© 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. 48724
    Prev
    Next
    INDEX
    Explanations

    case-control studies

    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
    æĥħåĨµè¿Ľè¡Į
    -0.14
    ä¼¼çļĦ
    -0.08
     pinch
    -0.08
    è¿¥
    -0.08
     Gay
    -0.08
    æĿł
    -0.08
    le
    -0.08
    ellig
    -0.08
    对ä»ĸ们
    -0.07
    _sdk
    -0.07
    POSITIVE LOGITS
    è°ĥæŁ¥æĺ¾ç¤º
    0.12
    (ft
    0.10
    çłĶ究表æĺİ
    0.09
    èĢĮå·²
    0.09
    è¶Ĭæĺ¯
    0.09
    æĢ§å¼º
    0.09
    èµĦæĸĻæĺ¾ç¤º
    0.09
    inges
    0.09
    PELL
    0.09
    yles
    0.09
    Activations Density 0.278%

    No Known Activations