© 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. 24108
    Prev
    Next
    INDEX
    Explanations

    happen to or with

    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
    èģª
    -0.09
    .ma
    -0.09
    ardy
    -0.08
    æĸĩç«łæĿ¥æºIJ
    -0.08
    udos
    -0.08
    cents
    -0.08
    åİ»çľĭ
    -0.08
    ody
    -0.08
    acha
    -0.08
    ä¿Ł
    -0.08
    POSITIVE LOGITS
     Toro
    0.10
    çĦ¯
    0.09
    è·µ
    0.09
    åĬ«
    0.09
    sed
    0.09
    IGATION
    0.09
    ä¸įåIJĮç¨ĭ度
    0.08
    asted
    0.08
    æı£
    0.08
    .persist
    0.08
    Activations Density 0.089%

    No Known Activations