© 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. 7073
    Prev
    Next
    INDEX
    Explanations

    numbers and currency symbols

    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
    Negative Logits
    ת×Ļ
    -0.07
    ients
    -0.07
     Legg
    -0.07
    eced
    -0.07
    ething
    -0.07
    รà¸ĩà¹ģ
    -0.07
    éķĩéĿĻ
    -0.07
    entu
    -0.07
    ä¾¿åľ¨
    -0.07
    orst
    -0.07
    POSITIVE LOGITS
    æŁIJä¸Ģ
    0.07
    è¯¥æľº
    0.06
    è¿İ宾
    0.06
    æĽĩ
    0.06
    为该
    0.06
    æŁIJæŁIJ
    0.06
    æŁIJ
    0.06
    åħ¶äº§åĵģ
    0.06
    ¶
    0.06
    æ±ķ
    0.06
    Activations Density 0.023%

    No Known Activations