© 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. 58771
    Prev
    Next
    INDEX
    Explanations

    filled electron shells

    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
     ajar
    -0.08
     open
    -0.08
     raw
    -0.07
     persistent
    -0.07
    .delay
    -0.07
    åŁŁ
    -0.07
     realtime
    -0.07
    биÑĢ
    -0.07
    æľīåħ³æ³ķå¾ĭ
    -0.07
    imest
    -0.07
    POSITIVE LOGITS
    éĹŃåIJĪ
    0.08
     tertutup
    0.08
    ohl
    0.07
    è¸ıå®ŀ
    0.07
    å¹³æ¹ĸ
    0.07
    ANNEL
    0.07
    å¹³éĿĻ
    0.07
    quiet
    0.07
    åĨ·éĿĻ
    0.07
     tightly
    0.07
    Activations Density 0.001%

    No Known Activations