© 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. 25165
    Prev
    Next
    INDEX
    Explanations

    a finite form

    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
    :first
    -0.07
    icha
    -0.07
    uste
    -0.06
    ocytes
    -0.06
     ÑĢазной
    -0.06
    åħīæĺ¯
    -0.06
    ocks
    -0.06
    å¾ĹäºĨ
    -0.06
    å¾Ĺè¦ģ
    -0.06
     ÑĢазного
    -0.06
    POSITIVE LOGITS
    herits
    0.08
     веÑī
    0.08
    æĪij们ä¼ļ尽快
    0.07
    à¸Ķิ
    0.07
     nonzero
    0.07
    ÑħÑĢа
    0.07
    æĪijä¹Łåİ»
    0.07
    ç«łèĬĤ缮å½ķ
    0.07
    æ³ķå¾ĭåĪ¶åº¦
    0.07
    _proto
    0.07
    Activations Density 0.038%

    No Known Activations