© 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. 51047
    Prev
    Next
    INDEX
    Explanations

    suffix for words

    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
    æľºæŀĦåĴĮ
    -0.07
    ÄĻż
    -0.07
    æłij人
    -0.07
    ologische
    -0.07
    atz
    -0.07
    yu
    -0.07
    zhou
    -0.06
    гийн
    -0.06
    setting
    -0.06
    家åĸ»
    -0.06
    POSITIVE LOGITS
    æīĢåľ¨åįķä½į
    0.07
    mouseup
    0.06
    uré
    0.06
    åĪ©æĸ¯
    0.06
    ä¸įåĢ¼
    0.06
    ÑĢабоÑĤки
    0.06
    تاب
    0.06
    (ST
    0.06
    æīĢåľ¨åŁİå¸Ĥ
    0.06
    å¨Ł
    0.06
    Activations Density 0.006%

    No Known Activations