I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.
Generative Recursive Reasoning (GRAM)Interpretability tooling like the Jacobian Lens could be applied to probe the persistent latent states that GRAM's recursive reasoning models rely on.
Comparing 11 Different AI ModelsBoth items investigate Qwen model internals and outputs — the 11-model comparison examines behavioral outputs while the Jacobian Lens explores Qwen3.6-27B's internal representations.
Qwen 3.8 2.4T Mixture of Experts ModelNeuronpedia's Jacobian Lens tool is specifically designed to explore the internals of Qwen3 family models, making it a direct interpretability companion to this Qwen 3 MoE release
Emergent Introspective Awareness in Large Language ModelsBoth investigate internal model representations through activation-level analysis — Neuronpedia's Jacobian Lens explores feature spaces in Qwen3, while this paper injects concepts into activations to probe self-awareness, making them methodologically complementary mechanistic interpretability efforts.
Supported by
Compression is predictionMechanistic interpretability work like Jacobian Lens analysis implicitly relies on the compression-prediction equivalence — understanding how LLMs compress training data into weights explains what features like those in J-Space actually represent
mattwood.fyi