© 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. 23930
    Prev
    Next
    INDEX
    Explanations

    discrete, categorical, tuples, and data attributes

    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
    éĻ©äºĽ
    -0.08
    utils
    -0.08
    é«ĺé¢Ŀ
    -0.08
    ãĥĭãĤ¢
    -0.07
    ä¸įåĪ©
    -0.07
    olumbia
    -0.07
    اعÙĬ
    -0.07
    á»įc
    -0.07
    åľ¨æŃ¤æ¬¡
    -0.07
    æĿĤè°Ī
    -0.07
    POSITIVE LOGITS
    åı¯ä»¥æĺ¯
    0.08
    æķ°åѦ
    0.07
    æĬ½è±¡
    0.07
     alphanumeric
    0.07
     mathematical
    0.07
    missible
    0.07
    umer
    0.07
     mathematic
    0.06
    astr
    0.06
    вл
    0.06
    Activations Density 0.040%

    No Known Activations