© 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. 63988
    Prev
    Next
    INDEX
    Explanations

    density MOS

    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
    家åºĦ
    -0.07
    æ°¸åĴĮ
    -0.07
    åıĮèī²
    -0.07
    stract
    -0.07
    èĦļæīĭ
    -0.07
    abouts
    -0.07
    zew
    -0.07
    artal
    -0.07
    mack
    -0.07
    _logger
    -0.06
    POSITIVE LOGITS
    ç»Ŀ
    0.08
    ä¸įåIJĮæŶ
    0.07
    ocs
    0.07
    -ui
    0.07
    è»
    0.07
    bere
    0.07
    æĥľ
    0.07
    attering
    0.07
    iere
    0.06
    edium
    0.06
    Activations Density 0.001%

    No Known Activations