© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39416
    Prev
    Next
    INDEX
    Explanations

    United States District Court

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ¤
    -0.10
    åĩĢåĮĸ
    -0.09
    å§Ĭ妹
    -0.09
    åłª
    -0.09
    isen
    -0.09
    rag
    -0.08
    åĢ¼å¾Ĺåħ³æ³¨
    -0.08
     ground
    -0.08
    åŀ¢
    -0.08
    .tm
    -0.08
    POSITIVE LOGITS
    åĽ´
    0.09
    磾
    0.09
    .failure
    0.09
    å¥Ķ
    0.09
    PLAIN
    0.08
    主åħ¬
    0.08
    èĮ´
    0.08
    uden
    0.08
    å¿Ĵ
    0.08
    å»ºåĽ½
    0.08
    Activations Density 0.251%

    No Known Activations