© 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. 48915
    Prev
    Next
    INDEX
    Explanations

    weight and obesity

    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
    /respond
    -0.09
    chet
    -0.09
    ä¸įäºĨ
    -0.09
    åķĨä¼ļ
    -0.09
    æĭ¿æĿ¥
    -0.09
     Bá
    -0.08
    åIJĥäºı
    -0.08
    å¯Įè´µ
    -0.08
    å¥ī
    -0.08
    Webpack
    -0.08
    POSITIVE LOGITS
    åĭī
    0.11
    æī®æ¼Ķ
    0.09
    è¿Ń
    0.09
    å¯¹æľªæĿ¥
    0.08
    æĹłå¿§
    0.08
    åŁİå¸Ĥ建设
    0.08
    è¾½
    0.08
    ä¸ĵä¸ļæĬĢæľ¯
    0.08
    绿èĮ¶
    0.08
    èŁĴ
    0.08
    Activations Density 0.038%

    No Known Activations