© 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. 41008
    Prev
    Next
    INDEX
    Explanations

    quantifying prevalence or depth

    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
    æ¯
    -0.07
    éĽªçļĦ
    -0.07
    ervis
    -0.07
     Stats
    -0.07
    å¼ĢåIJİ
    -0.06
    éĻįéĽª
    -0.06
    å¤§éĽª
    -0.06
     backward
    -0.06
    üz
    -0.06
    _Custom
    -0.06
    POSITIVE LOGITS
    bras
    0.08
    åŁĭ
    0.08
    Cancellation
    0.08
     cancelled
    0.08
    avenport
    0.07
    èıľåĪĢ
    0.07
    æĪIJ交
    0.07
    ç»ŀ
    0.07
     cancellation
    0.07
    cking
    0.07
    Activations Density 0.015%

    No Known Activations