© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61177
    Prev
    Next
    INDEX
    Explanations

    top-level domains and url paths

    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
    andu
    -0.07
    ¯
    -0.06
    undry
    -0.06
    ã
    -0.06
    ä¸İåIJĮåѦ
    -0.06
    ä¸ĢåĽŀ
    -0.06
    éĺħè¯»æľ¬æĸĩåīį
    -0.06
    éģĭãģ³
    -0.06
    ard
    -0.06
    °
    -0.06
    POSITIVE LOGITS
    iews
    0.08
    steller
    0.07
     xá
    0.07
    ceaux
    0.07
    åĩŃçĿĢ
    0.07
    onet
    0.07
    ath
    0.07
    液æĻ¶å±ı
    0.07
    keley
    0.07
     ìľ¼
    0.07
    Activations Density 0.166%

    No Known Activations