© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7051
    Prev
    Next
    INDEX
    Explanations

    motor neuron physiology

    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
    寻æ±Ĥ
    -0.10
    æĮ¡
    -0.10
    éĻ¢
    -0.10
    è¿ĽåĨĽ
    -0.09
    èĮ«
    -0.08
    ä»Ģä¹Īäºĭ
    -0.08
    家åĽŃ
    -0.08
    elize
    -0.08
    身边
    -0.08
     flaming
    -0.08
    POSITIVE LOGITS
    è·¨è¶Ĭ
    0.11
    ç´¢
    0.10
    /Area
    0.09
     Accom
    0.09
    çī¹éķ¿
    0.08
    建åįİ
    0.08
    uyo
    0.08
    åĬłå¤§
    0.08
     double
    0.08
    ä¸įåIJĮ
    0.08
    Activations Density 0.336%

    No Known Activations