Reading the Model's Mind Mid-Inference
Most LLM observability stops at the API boundary: request in, tokens out, everything between is a sealed box. Mechanistic interpretability tries to open that box, reading a model's internal computation directly from its weights. This episode walks the full inference pipeline, explains the residual stream and the logit lens, and covers why individual neurons are mostly noise (polysemanticity and superposition) and how sparse autoencoders untangle them. Then it surveys the tooling that actually does this work — TransformerLens, nnsight, vLLM-Lens, and DMI-Lib — including the overhead numbers…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.