© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39431
    Prev
    Next
    INDEX
    Explanations

    title or headline

    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
    omore
    -0.08
    uldig
    -0.08
    jš
    -0.07
    uar
    -0.07
    ìĿĮìĿ´
    -0.07
    _streams
    -0.07
     contro
    -0.07
    åįĹåIJij
    -0.07
    zinho
    -0.07
    صÙģØ©
    -0.07
    POSITIVE LOGITS
     format
    0.07
    æł¼å¼ı
    0.07
     whichever
    0.07
    çļĦåħīèį£
    0.07
     Format
    0.07
    fen
    0.06
    format
    0.06
     followed
    0.06
    à¸Ľà¸²à¸ģ
    0.06
     Close
    0.06
    Activations Density 0.004%

    No Known Activations