© 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. 44206
    Prev
    Next
    INDEX
    Explanations

    generally, particularly, increasingly, approximately, partly

    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
    anza
    -0.07
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.07
     definitely
    -0.06
    escu
    -0.06
     albo
    -0.06
    ä¹ĭæīĢ以
    -0.06
    çļĦä¸ĢåĪĩéĥ½
    -0.06
     consistently
    -0.06
    arat
    -0.06
    ä¹ĭäºİ
    -0.06
    POSITIVE LOGITS
    udy
    0.08
    iswa
    0.08
    undy
    0.08
    cky
    0.08
    utnik
    0.08
    天边
    0.07
    çļĦæĸ¹æ³ķæĿ¥
    0.07
    idy
    0.07
    elm
    0.07
    人å¿ĥ弦
    0.07
    Activations Density 0.301%

    No Known Activations