© 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. 9289
    Prev
    Next
    INDEX
    Explanations

    mathematical 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
    çİ°åľºç¡®è®¤
    -0.07
    uern
    -0.07
    æĶ¤
    -0.07
    senz
    -0.07
    tai
    -0.07
    åĴĮåIJĮåѦ
    -0.06
    ElementException
    -0.06
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    -0.06
    ãĤ¼
    -0.06
    åĬªåĬĽæīĵéĢł
    -0.06
    POSITIVE LOGITS
    èĮģ
    0.07
    æ¯Ķèĩªå·±
    0.07
     prof
    0.07
    pal
    0.07
    èĢĮå·²
    0.07
    bal
    0.06
    полни
    0.06
    æľīåĪ«
    0.06
    ä¸İä»ĸ
    0.06
    ç«ĭ交
    0.06
    Activations Density 0.008%

    No Known Activations