{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T18:03:38Z","timestamp":1789322618052,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032384065","type":"print"},{"value":"9783032384072","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-38407-2_25","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:32:26Z","timestamp":1789320746000},"page":"312-323","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Extraction and\u00a0Analysis of\u00a0Multimodal Concepts in\u00a0Vision Language Models Through Sparse Autoencoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8777-7070","authenticated-orcid":false,"given":"Sergio","family":"Lanza","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9840-780X","authenticated-orcid":false,"given":"Jae Hee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1343-4775","authenticated-orcid":false,"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"25_CR1","doi-asserted-by":"publisher","unstructured":"Bau, D., Zhou, B., Khosla, A., Oliva, A., Torralba, A.: Network Dissection: quantifying interpretability of deep visual representations. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3319\u20133327. Honolulu, HI (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.354, https:\/\/ieeexplore.ieee.org\/document\/8099837","DOI":"10.1109\/CVPR.2017.354"},{"key":"25_CR2","unstructured":"Bereska, L., Gavves, S.: Mechanistic interpretability for AI safety - a review. Trans. Mach. Learn. Res. (2024). https:\/\/openreview.net\/forum?id=ePUVetPKu6"},{"key":"25_CR3","unstructured":"Bricken, T., Templeton, A., Batson, J., Chen, B., Jermyn, A.: Adam: towards monosemanticity: decomposing language models with dictionary learning (2023). https:\/\/transformer-circuits.pub\/2023\/monosemantic-features"},{"key":"25_CR4","doi-asserted-by":"publisher","unstructured":"Cunningham, H., Ewart, A., Riggs, L., Huben, R., Sharkey, L.: Sparse autoencoders find highly interpretable features in language models. arXiv preprint arXiv:2309.08600 (Oct 2023). https:\/\/doi.org\/10.48550\/arXiv.2309.08600, https:\/\/arxiv.org\/abs\/2309.08600","DOI":"10.48550\/arXiv.2309.08600"},{"key":"25_CR5","doi-asserted-by":"publisher","unstructured":"Elhage, N., et al.: Toy models of superposition. arXiv preprint arXiv:2209.10652 (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.10652, https:\/\/arxiv.org\/abs\/2209.10652","DOI":"10.48550\/arXiv.2209.10652"},{"key":"25_CR6","doi-asserted-by":"publisher","unstructured":"Gao, L., et al.: Scaling and evaluating sparse autoencoders. arXiv preprint arXiv:2406.04093 (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.04093, https:\/\/arxiv.org\/abs\/2406.04093","DOI":"10.48550\/arXiv.2406.04093"},{"key":"25_CR7","unstructured":"Grattafiori, A., et\u00a0al.: The Llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"25_CR8","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, vol.\u00a0139, pp. 4904\u20134916 (2021). https:\/\/proceedings.mlr.press\/v139\/jia21b.html"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Kaduri, O., Bagon, S., Dekel, T.: What\u2019s in the image? A deep-dive into the vision of vision language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14549\u201314558 (2025). https:\/\/openaccess.thecvf.com\/content\/CVPR2025\/html\/Kaduri_Whats_in_the_Image_A_Deep-Dive_into_the_Vision_of_CVPR_2025_paper.html","DOI":"10.1109\/CVPR52734.2025.01356"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Lee, J.H., Lanza, S., Wermter, S.: From neural activations to concepts: a survey on explaining concepts in neural networks (2024). https:\/\/neurosymbolic-ai-journal.com\/system\/files\/nai-paper-697.pdf","DOI":"10.3233\/NAI-240743"},{"key":"25_CR11","doi-asserted-by":"publisher","unstructured":"Lim, H., Choi, J., Choo, J., Schneider, S.: Sparse autoencoders reveal selective remapping of visual concepts during adaptation. arXiv preprint arXiv:2412.05276 (2025). https:\/\/doi.org\/10.48550\/arXiv.2412.05276, https:\/\/arxiv.org\/abs\/2412.05276","DOI":"10.48550\/arXiv.2412.05276"},{"key":"25_CR12","unstructured":"Liu, H., et al.: LLaVA-NeXT: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"25_CR13","doi-asserted-by":"publisher","unstructured":"Ma, P., Rietdorf, L., Kotovenko, D., Hu, V.T., Ommer, B.: Does VLM classification benefit from LLM description semantics? In: Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence (2025). https:\/\/doi.org\/10.1609\/aaai.v39i6.32638, https:\/\/doi.org\/10.1609\/aaai.v39i6.32638","DOI":"10.1609\/aaai.v39i6.32638"},{"key":"25_CR14","doi-asserted-by":"publisher","unstructured":"Pach, M., Karthik, S., Bouniot, Q., Belongie, S., Akata, Z.: Sparse autoencoders learn monosemantic Features in vision-language models. In: Poster on Neural Information Processing Systems (NeurIPS 2025) (2025). https:\/\/doi.org\/10.48550\/arXiv.2504.02821, https:\/\/neurips.cc\/virtual\/2025\/loc\/san-diego\/poster\/119210","DOI":"10.48550\/arXiv.2504.02821"},{"key":"25_CR15","unstructured":"Park, D.H., et al.: Multimodal explanations: justifying decisions and pointing to the evidence. In: CoRR (2018). http:\/\/arxiv.org\/abs\/1802.08129"},{"key":"25_CR16","doi-asserted-by":"publisher","unstructured":"Paulo, G., Mallen, A., Juang, C., Belrose, N.: Automatically interpreting millions of features in large language models. arXiv preprint arXiv:2410.13928 (2024). https:\/\/doi.org\/10.48550\/arXiv.2410.13928, https:\/\/arxiv.org\/abs\/2410.13928","DOI":"10.48550\/arXiv.2410.13928"},{"key":"25_CR17","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, vol.\u00a0139, pp. 8748\u20138763 (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"25_CR18","doi-asserted-by":"publisher","unstructured":"Sim, M.Y., Zhang, W.E., Dai, X., Fang, B.: Can VLMs actually see and read? A survey on modality collapse in vision-language models. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 24452\u201324470. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.1256, https:\/\/aclanthology.org\/2025.findings-acl.1256\/","DOI":"10.18653\/v1\/2025.findings-acl.1256"},{"key":"25_CR19","unstructured":"Zang, Y., Yun, T., Tan, H., Bui, T., Sun, C.: Pre-trained vision-language models learn discoverable visual concepts. Trans. Mach. Learn. Res. (2025). https:\/\/openreview.net\/forum?id=Vq0wMFBjo2"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, K., Shen, Y., Li, B., Liu, Z.: Large multimodal models can interpret features in large multimodal models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025). https:\/\/openaccess.thecvf.com\/content\/ICCV2025\/papers\/Zhang_Large_Multi-modal_Models_Can_Interpret_Features_in_Large_Multi-modal_Models_ICCV_2025_paper.pdf","DOI":"10.1109\/ICCV51701.2025.00348"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38407-2_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:32:30Z","timestamp":1789320750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38407-2_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"ISBN":["9783032384065","9783032384072"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38407-2_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"assertion":[{"value":"14 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Padua","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}