© 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. 37575
    Prev
    Next
    INDEX
    Explanations

    preceding or starting position

    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
    ç»ıæµİåľĪ
    -0.08
    өн
    -0.07
    hoven
    -0.07
    otti
    -0.07
     Zy
    -0.07
    çIJĨè®ºåŁºç¡Ģ
    -0.07
    è´¸æĺĵåķĨ
    -0.07
    anson
    -0.07
     matern
    -0.07
    boden
    -0.07
    POSITIVE LOGITS
    ç´§è·Ł
    0.08
    ç®ĢçŁŃ
    0.08
    å¾Ģå¾Ģæĺ¯
    0.08
    éĢļ常æĺ¯
    0.08
    åľ°åIJį
    0.08
    主è¯Ń
    0.08
     preceded
    0.08
    ç´§éļı
    0.08
    åīįç½®
    0.08
     preceding
    0.07
    Activations Density 0.029%

    No Known Activations