© 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. 37725
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers

    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
    æ´¾åĩºæīĢæ°ijèѦ
    -0.08
     ...\
    -0.07
     ..."
    -0.07
    ---</
    -0.07
    olson
    -0.07
    <context
    -0.07
    olim
    -0.07
    ...*
    -0.07
     (...)
    -0.07
    (||
    -0.07
    POSITIVE LOGITS
    istar
    0.07
    RGBA
    0.07
    æĪĸåħ¶
    0.07
    []
    0.07
    ä¹ĭéķ¿
    0.07
    duced
    0.06
    èıģ
    0.06
     WINAPI
    0.06
    .Builder
    0.06
    .prototype
    0.06
    Activations Density 0.164%

    No Known Activations