© 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. 2540
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    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
    kaar
    -0.10
    onor
    -0.10
    ç¢Ľ
    -0.10
    ä¸Ģå¹ķ
    -0.10
    ilogy
    -0.10
    afia
    -0.10
    bose
    -0.10
    æ»Ĺ
    -0.09
    /problems
    -0.09
    pleasant
    -0.09
    POSITIVE LOGITS
    ,
    0.08
     either
    0.08
    ä½łçŁ¥éģĵ
    0.08
    ;
    0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    0.07
    .
    0.07
    æŁIJç§į
    0.07
     (
    0.06
    身ä¸Ĭ
    0.06
    çļĦ身影
    0.06
    Activations Density 2.890%

    No Known Activations