© 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. 63851
    Prev
    Next
    INDEX
    Explanations

    gay and lesbian identities

    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
    enance
    -0.08
    влек
    -0.08
    çīĸ
    -0.08
     أع
    -0.08
    åijĺ
    -0.08
    _ENTITY
    -0.08
     rh
    -0.08
    æ¸ħæľĿ
    -0.08
    lem
    -0.08
    æĸŃè£Ĥ
    -0.08
    POSITIVE LOGITS
    /o
    0.09
    à¨ľ
    0.09
    彩
    0.09
    åIJĦè¡Į
    0.09
    媾
    0.09
    erging
    0.09
    ILE
    0.08
    omics
    0.08
    rette
    0.08
    ×Ļ×ķת
    0.08
    Activations Density 0.003%

    No Known Activations