© 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. 57348
    Prev
    Next
    INDEX
    Explanations

    language, materials, philosopher, component

    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
    ادر
    -0.08
    лÑıн
    -0.07
    æŁIJ天
    -0.07
    kind
    -0.07
    æĸ¹æ³ķä¸İ
    -0.07
    éĹ®é¢ĺæŶ
    -0.07
    åıªæĺ¯ä¸Ģç§į
    -0.07
    .TYPE
    -0.07
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    -0.07
    ิà¸Ĭ
    -0.06
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.09
    çļĦè¿ĺæľī
    0.09
    èİ«è¿ĩäºİ
    0.09
    éĤ£å°±æĺ¯
    0.08
     namens
    0.08
    çļĦæĺ¯
    0.08
    ãģ®ãģĮ
    0.08
    ãģªãģ®ãģĮ
    0.08
    ìŀIJìĿ¸
    0.08
    ìŀ¬ìĿ¸
    0.08
    Activations Density 0.362%

    No Known Activations