© 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. 13126
    Prev
    Next
    INDEX
    Explanations

    World Series

    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
    ------------------------------------------------------------------------------------------------
    -0.07
    çļĻ
    -0.07
    ================================
    -0.07
    代
    -0.07
    缴åįĩ
    -0.07
    ì´Ī
    -0.07
    __))
    -0.07
    bella
    -0.07
    ********************************************************************************
    -0.06
    elon
    -0.06
    POSITIVE LOGITS
    uros
    0.07
    byn
    0.06
    äter
    0.06
     Judgment
    0.06
    .ua
    0.06
    UIT
    0.06
    sj
    0.06
    etul
    0.06
    iasm
    0.06
    æīĢå±ŀåĪĨç±»
    0.06
    Activations Density 0.064%

    No Known Activations