https://mbrenndoerfer.com/writing/mechanistic-interpretability/mechanistic-interpretability2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/circuits-the-unit-of-analysis2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/how-circuits-are-discovered2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/induction-heads-a-canonical-example2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/other-mechanistic-discoveries2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/superposition-and-polysemanticity2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/the-linear-representation-hypothesis2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/code-implementation2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/implications-for-ai-safety-and-alignment2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/limitations-and-challenges2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/summary2026-03-20T17:30:18.000Zhttps://mbrenndoerfer.com/writing/mechanistic-interpretability/quiz2026-03-20T17:30:18.000Z