© 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. 18356
    Prev
    Next
    INDEX
    Explanations

    operative video, recognition system, delegate style, validation not, data from, XML REQUEST, disable not, made for, function plot, diagnosis using

    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
    åı¯æĥ³èĢĮçŁ¥
    -0.07
    åĪĻ该
    -0.07
    åĪĻæľī
    -0.07
    对æѤ
    -0.07
    åIJİèĢħ
    -0.07
    æĢ§æĪĸ
    -0.07
    ächt
    -0.07
    agens
    -0.07
    ilon
    -0.07
    ibri
    -0.07
    POSITIVE LOGITS
    ãģ¨ãģĦãģĨãģĭ
    0.07
    åľ¨ç»Ļ
    0.07
    榻
    0.07
    家家
    0.06
     utilisation
    0.06
    æłĩåĩĨä¿¡æģ¯
    0.06
    âĢIJ
    0.06
    Ĩµ
    0.06
    ãģ¨ãģĦãģĨãģĵãģ¨ãģ§
    0.06
    ä»ĸæĬĬ
    0.06
    Activations Density 0.038%

    No Known Activations