© 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. 31145
    Prev
    Next
    INDEX
    Explanations

    float and double types

    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
    æĽ´å¤ļ精彩åĨħ容
    -0.07
    ØŃدÙĬØ«
    -0.07
    ÑĩаÑģÑĤи
    -0.07
    edImage
    -0.07
    кола
    -0.07
    ç±»çŃī
    -0.07
    celer
    -0.07
    è¡ĮçŁ¥
    -0.07
    <src
    -0.07
    LOSE
    -0.07
    POSITIVE LOGITS
    ä¸ĢèĪ¬
    0.07
    å£
    0.06
     ë§Ī리
    0.06
    ç´¯
    0.06
    ê²Į
    0.06
    agos
    0.06
    ubi
    0.06
    ç§ijæĬĢåıijå±ķæľīéĻIJåħ¬åı¸
    0.06
    ä¸Ģçīĩ
    0.06
    好å¿ĥ
    0.06
    Activations Density 0.012%

    No Known Activations