© 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. 11198
    Prev
    Next
    INDEX
    Explanations

    without replacement from

    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
    工伤
    -0.08
    åŃĹæł·
    -0.08
    Shock
    -0.08
     Nath
    -0.08
    ยà¸Ńà¸Ķ
    -0.08
    èĽĭ
    -0.08
    æĹłæīĢ
    -0.08
    å¥
    -0.07
    ASC
    -0.07
    PIO
    -0.07
    POSITIVE LOGITS
    nor
    0.11
    uve
    0.10
    ivor
    0.10
    èķĥ
    0.10
    ilinear
    0.09
    å¯¹ä½ł
    0.09
    .setCursor
    0.09
    à¸ŀล
    0.09
    达人
    0.08
    çīĪæĿĥæīĢæľī
    0.08
    Activations Density 0.003%

    No Known Activations