© 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. 56099
    Prev
    Next
    INDEX
    Explanations

    municipality, commune, township,

    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
    轨
    -0.10
    骡
    -0.10
    è¾£
    -0.09
    éĺī
    -0.09
    é¢ł
    -0.09
    çĿĢä»ĸ
    -0.09
    .sav
    -0.09
    closure
    -0.09
    ä»İæľª
    -0.09
    closing
    -0.09
    POSITIVE LOGITS
    æĿijåŃIJ
    0.10
    å«Į
    0.09
    èĥ½çľĭåĩº
    0.09
    åŁŃ
    0.08
    æĹºçĽĽ
    0.08
    åģİ
    0.08
    é£İéĻ©ç®¡çIJĨ
    0.08
    æݧèĤ¡
    0.08
    å¸ĤæĶ¿
    0.08
    å¹²äºĭ
    0.08
    Activations Density 0.244%

    No Known Activations