© 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. 47815
    Prev
    Next
    INDEX
    Explanations

    b quark or c quark

    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
    åıĮèĸª
    -0.08
    OLS
    -0.07
    atti
    -0.07
    apan
    -0.07
    лко
    -0.07
     Morton
    -0.07
    åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    æ°§åĮĸ碳
    -0.07
    acons
    -0.06
    åı¯æĥ³
    -0.06
    POSITIVE LOGITS
    ä¸īå°º
    0.07
    /\
    0.07
    åĴĮ大
    0.07
    æĺĵåľ°
    0.07
    ä¸İ大
    0.06
    åŁº
    0.06
    è½
    0.06
    aising
    0.06
    xFFFFFF
    0.06
    åĴĮ西
    0.06
    Activations Density 0.002%

    No Known Activations