© 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. 64035
    Prev
    Next
    INDEX
    Explanations

    bar, bars, bartending

    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
    æīŃ磩
    -0.10
     Chall
    -0.09
    èĢĻ
    -0.09
    庾
    -0.09
    YLE
    -0.09
    iever
    -0.09
     Overs
    -0.09
    KeyName
    -0.09
    .Dom
    -0.09
    overrides
    -0.09
    POSITIVE LOGITS
    strup
    0.09
    åIJĥè¿ĩ
    0.09
    éĽ¾
    0.09
    æľīæĿĥ
    0.08
    ç»ıæµİåŃ¦å®¶
    0.08
    èĭį
    0.08
    Animations
    0.08
    åŀĴ
    0.08
    agra
    0.08
    ç»ıæµİæĬĢæľ¯
    0.08
    Activations Density 0.048%

    No Known Activations