© 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. 59976
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    Negative Logits
    uron
    -0.08
    ksen
    -0.07
     Jour
    -0.07
    æľ¬æĸĩéĵ¾æİ¥
    -0.07
    пÑĢоек
    -0.07
    ãĥĥãĤ³
    -0.07
    सन
    -0.07
    adow
    -0.07
    TargetException
    -0.07
    riba
    -0.07
    POSITIVE LOGITS
     straightforward
    0.07
     Freih
    0.07
    nu
    0.06
    alp
    0.06
    zion
    0.06
    åIJĦ个æĸ¹éĿ¢
    0.06
     manip
    0.06
     Observ
    0.06
     meaningful
    0.06
    .Site
    0.06
    Activations Density 0.457%

    No Known Activations