© 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. 10706
    Prev
    Next
    INDEX
    Explanations

    sketch comedy

    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
    åĪ¸
    -0.10
    åĨł
    -0.09
    isbn
    -0.09
    -public
    -0.09
    dden
    -0.09
    æĦ¤
    -0.08
    erable
    -0.08
    antal
    -0.08
     dokÅĤadnie
    -0.08
     Atkins
    -0.08
    POSITIVE LOGITS
    æĺ¥æĻļ
    0.10
    éªĸ
    0.09
    _ARCHIVE
    0.08
     Schneider
    0.08
    _archive
    0.08
    åĴĮæľįåĬ¡
    0.08
    éĢī
    0.08
    çĿ¡è§ī
    0.08
    绸
    0.08
    æĥħ趣
    0.08
    Activations Density 0.126%

    No Known Activations