© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55262
    Prev
    Next
    INDEX
    Explanations

    boolean properties like default, false, or on

    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
    æ¯Ķ以åīį
    -0.08
    илÑĮ
    -0.07
    acca
    -0.07
    ÑĢиÑĦ
    -0.07
    emics
    -0.07
    æĿī
    -0.07
    æ¯Ķåݻ年
    -0.07
    æĤ¨çļĦä½įç½®
    -0.07
    orf
    -0.07
    ajor
    -0.07
    POSITIVE LOGITS
     initially
    0.13
    åĪĿå§ĭ
    0.12
    é»ĺ认
    0.11
    ä¹ĭåĪĿ
    0.11
     inicialmente
    0.10
     Initially
    0.10
     изнаÑĩалÑĮно
    0.10
    Initially
    0.09
    default
    0.09
     inizialmente
    0.09
    Activations Density 0.082%

    No Known Activations