© 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. 26181
    Prev
    Next
    INDEX
    Explanations

    hold events or discussions

    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
    terr
    -0.09
    ecn
    -0.09
    Ñģлов
    -0.09
    ä¸ĢåĢĭ人
    -0.09
    ìĬ¨
    -0.09
    ä¹İ
    -0.09
     mou
    -0.09
    åĽĬ
    -0.08
    忤
    -0.08
    ypes
    -0.08
    POSITIVE LOGITS
    /do
    0.10
    inger
    0.09
    ers
    0.09
    overs
    0.09
     sway
    0.09
    两次
    0.09
    ings
    0.08
    ì²ĺ
    0.08
    mate
    0.08
     survivor
    0.08
    Activations Density 0.019%

    No Known Activations