© 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. 4741
    Prev
    Next
    INDEX
    Explanations

    citation year followed by publication

    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
    大计
    -0.08
     Freib
    -0.07
    å§ĭèĩ³
    -0.07
    ×Ĺ×Ļ
    -0.07
    æĸĩéĿĻ
    -0.06
    以ä¸ĭ为
    -0.06
    nez
    -0.06
    æ³¢æ¾ľ
    -0.06
    ais
    -0.06
    ru
    -0.06
    POSITIVE LOGITS
    ujui
    0.07
    ائÙĬØ©
    0.06
    æľīç¼ĺ
    0.06
    ä½łä¸įçŁ¥éģĵ
    0.06
     unpublished
    0.06
    /tutorial
    0.06
    bli
    0.06
    _ca
    0.06
    /report
    0.06
    æŶéĹ´åıĬ
    0.06
    Activations Density 0.054%

    No Known Activations