© 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. 15592
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    ç©·
    -0.08
    à¸Ĺุà¸ģà¸Ħà¸Ļ
    -0.07
    /devices
    -0.06
    æľ¬åľ°åĮº
    -0.06
    ä¸ĩåĽ½
    -0.06
    çļĦ设计é£İæł¼
    -0.06
    coni
    -0.06
    eteg
    -0.06
    å¤ĸè§Ĥ设计
    -0.06
    Otherwise
    -0.06
    POSITIVE LOGITS
    ULE
    0.07
    ahal
    0.07
    æ²
    0.07
    æĭĴ
    0.07
    zien
    0.07
    åIJĪ
    0.07
    usher
    0.07
    _;
    0.07
    æĭĴç»Ŀ
    0.07
    æĭ
    0.07
    Activations Density 0.155%

    No Known Activations