@inproceedings{neo-etal-2026-spectra,
    title = "Spectra: A Mechanistic Interpretability Library for Vision-Language Models",
    author = "Neo, Clement  and
      Zheng, Yongsen  and
      Lam, Kwok-Yan  and
      Ong, Luke",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.78/",
    pages = "794--803",
    ISBN = "979-8-89176-392-0",
    abstract = "Vision-Language Models (VLMs) have become increasingly important in AI applications, yet interpretability tools for these models lag behind those available for text-only language models. While libraries like TransformerLens have enabled significant progress in understanding language models, existing tools for VLMs are limited to basic activation probing and saving. We introduce Spectra, a library specifically designed for mechanistic interpretability of VLMs that provides unified abstractions for activation patching, attention pattern analysis, and meta-functions across diverse VLM architectures. Built on HuggingFace{'}s Transformers, our library handles architecture-specific complexities through per-checkpoint configurations while maintaining a simple, high-level interface. We demonstrate the library{'}s capabilities by performing interpretability experiments on a counting task, showing how researchers can easily perform experiments that were previously cumbersome to do. The library currently supports Qwen2.5-VL, Qwen3-VL, LLaVA 1.5 and SmolVLM, with a design that facilitates extension to additional architectures. The library can be found at \url{github.com/clemneo/vlm-spectra}."
}