© 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. 16733
    Prev
    Next
    INDEX
    Explanations

    Jay-Z

    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
    hall
    -0.09
    æĭ¿æĿ¥
    -0.09
    .fold
    -0.09
    iesel
    -0.09
    ennen
    -0.09
    强èĢħ
    -0.08
    åĢ©
    -0.08
     бÑĥм
    -0.08
    åĪĨ为
    -0.08
    æī¹å¤į
    -0.08
    POSITIVE LOGITS
    ippy
    0.09
    æķĻåŃ¦è´¨éĩı
    0.09
    éĿ´
    0.09
    æ±Łæ¹ĸ
    0.08
    ä¸Ģåī¯
    0.08
    ç¼ł
    0.08
    åIJĦ项
    0.08
     strSql
    0.08
    ØŃÙĦ
    0.08
    ä¸Ģ头
    0.08
    Activations Density 0.004%

    No Known Activations