@inproceedings{weng-etal-2026-safe,
    title = "Safe-{SAIL}: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework",
    author = "Weng, Jiaqi  and
      Zheng, Han  and
      Zhang, Hanyu  and
      Zhou, Ej  and
      He, Qinqin  and
      Tao, Jialing  and
      Xue, Hui  and
      Chu, Zhixuan  and
      Wang, Xiting",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.944/",
    pages = "18916--18935",
    ISBN = "979-8-89176-395-1"
}