© 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. 55824
    Prev
    Next
    INDEX
    Explanations

    units of measurement or range

    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
    ç¼¥
    -0.07
    æĿĪ
    -0.07
    æ½ľåľ¨çļĦ
    -0.06
    åģļåĩºäºĨ
    -0.06
     Hoh
    -0.06
    è¦ģä¹Ī
    -0.06
    åī¯ç§ĺ书éķ¿
    -0.06
     either
    -0.06
    å¦Ĥä½ķåģļ
    -0.06
    heus
    -0.06
    POSITIVE LOGITS
     comparable
    0.09
     Comparable
    0.08
     averaged
    0.08
    Comparable
    0.08
    çŃī主è¦ģ
    0.08
    åĮĹä¸Ĭ
    0.08
    orra
    0.07
     averages
    0.07
    äºĮåįģ大
    0.07
    ä¸ĭåIJĮ
    0.07
    Activations Density 0.215%

    No Known Activations