© 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. 60047
    Prev
    Next
    INDEX
    Explanations

    This file is part of

    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
    Not in Any Lists

    No Comments

    Negative Logits
    atively
    -0.09
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.08
    è¿Ļæĺ¯å¯¹
    -0.08
    è¿Ļä¸ľè¥¿
    -0.07
    à¹Īà¸ĩ
    -0.07
    è¿Ļåı¯èĥ½
    -0.07
    è¿Ļå°ıåŃIJ
    -0.07
    å°±æĢķ
    -0.07
    dest
    -0.07
    หà¸Ļà¹īาà¸Ļีà¹ī
    -0.07
    POSITIVE LOGITS
     yüzden
    0.11
    /her
    0.11
     ultimi
    0.10
     ÙĥÙĦÙĩ
    0.10
    /th
    0.10
     nedenle
    0.09
    ullet
    0.09
     konuda
    0.09
    Úº
    0.09
     particular
    0.09
    Activations Density 0.526%

    No Known Activations