© 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. 55247
    Prev
    Next
    INDEX
    Explanations

    Alan Turing, fedorqui, Magnusson, Trigaux

    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
    uage
    -0.08
    躯
    -0.07
     nigeria
    -0.07
     Javas
    -0.07
    _hooks
    -0.07
     {?
    -0.07
    ç³Ļ
    -0.07
    rog
    -0.07
    úl
    -0.07
     brutto
    -0.07
    POSITIVE LOGITS
    æĻ©
    0.07
     Pat
    0.07
    Pat
    0.07
    pat
    0.06
    irim
    0.06
    ieso
    0.06
     SPDX
    0.06
    il
    0.06
    çijľ
    0.06
    åĬłå¾®ä¿¡
    0.06
    Activations Density 0.058%

    No Known Activations