© 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. 14395
    Prev
    Next
    INDEX
    Explanations

    levels, size, or diameter

    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
    usak
    -0.08
    åĿĬ
    -0.07
     licked
    -0.07
    SEM
    -0.07
    åı¯è´µ
    -0.06
    /latest
    -0.06
    è¿Ļç§įä¸ľè¥¿
    -0.06
    çľĭåľ¨çľ¼éĩĮ
    -0.06
    æľ¬æ³ķ
    -0.06
    ä¸Ĭå¸ĤåIJİ
    -0.06
    POSITIVE LOGITS
     realistic
    0.08
     simulations
    0.08
    benchmark
    0.08
    _codegen
    0.08
     resolutions
    0.08
    幡
    0.08
    rot
    0.08
    åĽºå®ļ
    0.08
    fixed
    0.08
    -builder
    0.07
    Activations Density 0.218%

    No Known Activations