© 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. 65457
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    并èĮĤ
    -0.08
    ette
    -0.08
    ÑĢик
    -0.07
    lette
    -0.07
    eer
    -0.07
    ITTER
    -0.07
    entrum
    -0.07
    ETTE
    -0.07
    _lite
    -0.07
    è¾ĥåݻ年åIJĮæľŁ
    -0.07
    POSITIVE LOGITS
    .gov
    0.07
    ä¸ĬçļĦ
    0.07
    -wide
    0.07
    ç©
    0.07
    -based
    0.07
    åIJī
    0.07
    -specific
    0.07
    aidu
    0.07
    -only
    0.07
    egov
    0.07
    Activations Density 0.002%

    No Known Activations