© 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. 34136
    Prev
    Next
    INDEX
    Explanations

    groups of people, organizations, or entities

    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
    å¾ľå¾ī
    -0.08
    atalog
    -0.07
    maks
    -0.06
     اÙĦØ£ÙħÙħ
    -0.06
    attie
    -0.06
    _creator
    -0.06
    设计ä¸Ń
    -0.06
    abies
    -0.06
    ç®ķ
    -0.06
    å¦ĤæľŁ
    -0.06
    POSITIVE LOGITS
    为主ä½ĵçļĦ
    0.09
    èĩªåıij
    0.08
    群ä½ĵ
    0.08
    (Control
    0.08
    olders
    0.08
    åĴĮéĥ¨åĪĨ
    0.08
    ä¸į满
    0.08
    主æĮģåı¬å¼Ģ
    0.08
    ç»ĦæĪIJçļĦ
    0.07
    åħ±åIJĮåıĤä¸İ
    0.07
    Activations Density 0.206%

    No Known Activations