--- title: Sparse Autoencoders description: AI notes by Mrinaal Arora tagged "Sparse Autoencoders" updated: 2026-06-12 canonical: https://aroramrinaal.com/ai/tags/sparse-autoencoders source: https://aroramrinaal.com/ai/tags/sparse-autoencoders.md alternate: https://aroramrinaal.com/ai/tags/sparse-autoencoders/markdown --- # Sparse Autoencoders AI notes, small builds, and writeups by Mrinaal Arora tagged "Sparse Autoencoders". - Page: https://aroramrinaal.com/ai/tags/sparse-autoencoders - Markdown: https://aroramrinaal.com/ai/tags/sparse-autoencoders/markdown - Markdown (.md): https://aroramrinaal.com/ai/tags/sparse-autoencoders.md - All tags: https://aroramrinaal.com/ai/tags/markdown - Full AI index: https://aroramrinaal.com/ai/markdown - Posts with this tag: 1 of 19 - Co-occurring tags: Interpretability ## Posts - [Looking Inside Qwen3-4B With Sparse Autoencoders](https://aroramrinaal.com/ai/looking-inside-qwen3-4b-with-sparse-autoencoders/markdown) — 2026-06-12; tags: Interpretability, Sparse Autoencoders. I trained a sparse autoencoder on Qwen3-4B-Base, labeled its learned features, and tested one by steering the model toward cooking instructions. [HTML](https://aroramrinaal.com/ai/looking-inside-qwen3-4b-with-sparse-autoencoders)