© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23005
    Prev
    Next
    INDEX
    Explanations

    data type conversion and precision

    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
    iveness
    -0.07
    empo
    -0.07
    èļĮ
    -0.07
    emble
    -0.07
     ********************************************************************************
    -0.07
     dags
    -0.07
     NDEBUG
    -0.07
    çł´äº§éĩįæķ´
    -0.07
    akas
    -0.07
    -conf
    -0.06
    POSITIVE LOGITS
    রণ
    0.08
    cast
    0.07
     cast
    0.07
    æĪijåIJĥ
    0.07
    éĿĴæ¢ħ
    0.07
    温馨æıIJ示
    0.07
    èĢģèĢģå®ŀ
    0.07
     imported
    0.07
    å¿ĹåĪļ
    0.07
     import
    0.06
    Activations Density 0.012%

    No Known Activations