© 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. 64250
    Prev
    Next
    INDEX
    Explanations

    programming and calculus symbols

    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
    enko
    -0.08
    رÙĪÙĬ
    -0.07
    opl
    -0.07
    çħ²
    -0.06
    omitempty
    -0.06
    ห
    -0.06
    ernet
    -0.06
    åĬłå·¥å·¥èīº
    -0.06
    ä¸Ģç¬ij
    -0.06
     STDERR
    -0.06
    POSITIVE LOGITS
    æķ´
    0.09
    åIJĪåIJĮæŶ
    0.08
    å§ĭèĩ³
    0.08
    {}".
    0.07
    ulte
    0.07
    ×ŀת
    0.07
    人åijĺåľ¨
    0.07
    (()=>
    0.06
    æ²ĻåŃIJ
    0.06
     ×Ķ׼׾
    0.06
    Activations Density 0.013%

    No Known Activations