@inproceedings{he-etal-2026-saeexplainer,
    title = "{SAEE}xplainer: Interpreting {SAE} Features with Activation-Guided Preference Optimization",
    author = "He, Jingyi  and
      Zhao, Haiyan  and
      Shi, Ruxue  and
      Liu, Yanguang  and
      Wang, Xin  and
      Sun, Fei  and
      Du, Mengnan",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.393/",
    pages = "9019--9038",
    ISBN = "979-8-89176-459-0"
}