© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26304
    Prev
    Next
    INDEX
    Explanations

    male gender identification

    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
    Negative Logits
    elon
    -0.10
    ding
    -0.10
    rade
    -0.10
    ย
    -0.10
    enthal
    -0.09
    ом
    -0.09
    好人
    -0.09
    arians
    -0.09
    alem
    -0.09
    dued
    -0.09
    POSITIVE LOGITS
    volent
    0.24
    icious
    0.10
    itÃł
    0.10
    ities
    0.10
    avig
    0.10
    fic
    0.10
    ITY
    0.09
    åĮĸè¿Ľç¨ĭ
    0.09
    åIJĮèĥŀ
    0.09
    istic
    0.09
    Activations Density 0.038%

    No Known Activations