© 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. 25127
    Prev
    Next
    INDEX
    Explanations

    `. ` and programming constructs

    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
    ussin
    -0.08
     menyel
    -0.08
    æľĢæĸ°è¯Ħ论
    -0.08
    lande
    -0.08
    å¦Ĥæ°´
    -0.07
    umis
    -0.07
    민
    -0.07
    主è¦ģç»ıèIJ¥
    -0.07
    emers
    -0.07
    .tex
    -0.07
    POSITIVE LOGITS
     Example
    0.08
    å®ŀä¾ĭ
    0.07
    ç±»åŀĭçļĦ
    0.07
    ä¸įåIJĮç±»åŀĭçļĦ
    0.07
    /examples
    0.07
     Tid
    0.07
     illustrating
    0.07
    -example
    0.07
    _example
    0.06
    èĬ³
    0.06
    Activations Density 0.252%

    No Known Activations