© 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. 8163
    Prev
    Next
    INDEX
    Explanations

    sports betting wager

    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
    æĶ¯
    -0.09
    elj
    -0.08
    WARD
    -0.08
    åIJįåī¯
    -0.08
    é¢Ħéĺ²ä¸ºä¸»
    -0.07
    ISTI
    -0.07
    满åłĤ
    -0.07
    ÑĢек
    -0.07
    raries
    -0.07
    fu
    -0.07
    POSITIVE LOGITS
    endar
    0.07
    æİ¥åĪ°äºĨ
    0.06
    西åİ¿
    0.06
    FG
    0.06
    ¦
    0.06
    ائÙĩ
    0.06
    {return
    0.06
    azar
    0.06
    ³³³³³³³
    0.05
    lest
    0.05
    Activations Density 0.433%

    No Known Activations