© 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. 52003
    Prev
    Next
    INDEX
    Explanations

    languages and dialects

    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
    客
    -0.08
    è·¨
    -0.07
    æĺİæĺİæĺ¯
    -0.07
    клон
    -0.07
    ardini
    -0.06
     Grove
    -0.06
     américa
    -0.06
    éģĹ
    -0.06
    rain
    -0.06
    DSA
    -0.06
    POSITIVE LOGITS
    à°£
    0.08
    IMIT
    0.07
    å¾Ĺä¸Ĭ
    0.07
    zilla
    0.07
    pad
    0.07
    elat
    0.07
    å¯Į强
    0.07
    лÑıн
    0.07
    StringLength
    0.07
    onth
    0.07
    Activations Density 0.003%

    No Known Activations