© 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. 792
    Prev
    Next
    INDEX
    Explanations

    winning a game

    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
    æĥħæĦŁ
    -0.10
    fund
    -0.09
    ambre
    -0.09
     Baba
    -0.09
    สà¸ĸาà¸Ļ
    -0.09
    åijĺ
    -0.08
    orado
    -0.08
    lope
    -0.08
    éķĤ
    -0.08
    è¯Ŀ说
    -0.08
    POSITIVE LOGITS
    åħ¢
    0.09
    iren
    0.09
    éĿĻ
    0.09
    è¯Ĩ
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    åĹĵåŃIJ
    0.08
    stime
    0.08
    ç¥ĸçĪ¶
    0.08
    exter
    0.08
    rint
    0.08
    Activations Density 0.008%

    No Known Activations