© 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. 44532
    Prev
    Next
    INDEX
    Explanations

    non-Latin scripts and numbers

    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
    atile
    -0.06
    kent
    -0.06
    ething
    -0.06
    cius
    -0.06
    ç¥ł
    -0.06
    erne
    -0.06
    enius
    -0.06
    /sdk
    -0.06
    讨
    -0.06
    /lang
    -0.06
    POSITIVE LOGITS
    ายà¸Ļ
    0.08
    è¿ĶåĽŀ顶éĥ¨
    0.08
    ahkan
    0.07
    agentur
    0.07
    ikasi
    0.07
    ç¥ŀå±±
    0.07
    à¹Ħà¸Ľà¸ģวà¹Īา
    0.07
    ä¸ĵ家表示
    0.07
    ovina
    0.07
    bons
    0.07
    Activations Density 0.009%

    No Known Activations