anicka/jlens-qwen2.5-7b-instruct

Jacobian lens for Qwen 2.5 7B Instruct

Fitted with Anthropic's reference implementation (jacobian-lens, Apache-2.0) for the paper Verbalizable Representations Form a Global Workspace in Language Models (2026). Averaged input-output Jacobians per layer over wikitext-103 prompts (fit_qwen25_7b.py from that repo).

Usage:

import jlens
lens = jlens.JacobianLens.from_pretrained(
    "anicka/jlens-qwen2.5-7b-instruct",
    filename="qwen2.5-7b-instruct_jlens.pt")

Companion notebook (three lenses on one activation — logit lens vs Jacobian lens vs NLA): https://github.com/anicka-net/nla-at-home/blob/main/notebooks/05_three_lenses.ipynb