© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52157
    Prev
    Next
    INDEX
    Explanations

    difference and exception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     fullest
    -0.08
    è¿Ļä¸ĢéĹ®é¢ĺ
    -0.07
    ä¸įæŃ£å¸¸
    -0.07
    å°Ķ夫
    -0.07
    å¾Ļ
    -0.07
    æĻ®éĢļ
    -0.07
    å¾Ĵ
    -0.07
    iru
    -0.06
    é«ĺä½İ
    -0.06
    æīĢå¾Ĺ
    -0.06
    POSITIVE LOGITS
     stylist
    0.08
     ÙĤÙĦÙĬ
    0.08
     minor
    0.08
     slight
    0.08
    ä¸įåIJĮçļĦæĺ¯
    0.08
    дли
    0.08
    çķ¥æĺ¾
    0.08
    ç»Ĩå¾®
    0.08
     occas
    0.08
    avras
    0.08
    Activations Density 0.038%

    No Known Activations