© 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. 63426
    Prev
    Next
    INDEX
    Explanations

    French Grand Prix

    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
     Anc
    -0.07
    ä¸Ģèµ·åľ¨
    -0.07
     resting
    -0.06
    colas
    -0.06
    ouch
    -0.06
    伤çļĦ
    -0.06
    èIJ½ãģ¨
    -0.06
    zs
    -0.06
    رÙĪس
    -0.06
    .optional
    -0.06
    POSITIVE LOGITS
    ä¸Ģå¼ı
    0.08
    ORED
    0.07
     Variation
    0.07
    符åIJĪæĿ¡ä»¶
    0.07
    (QtCore
    0.07
    oline
    0.07
    ahl
    0.07
    å½Ī
    0.07
     Fare
    0.07
    .charset
    0.07
    Activations Density 0.007%

    No Known Activations