© 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. 55159
    Prev
    Next
    INDEX
    Explanations

    numbers, multiplication, addition, subtraction

    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
    ç²¾
    -0.07
    ytu
    -0.07
    å·¥åķĨ注åĨĮ
    -0.06
    æĸŃ
    -0.06
     ÙĪÙĦÙĬ
    -0.06
     Äijá»Ĺ
    -0.06
    人工
    -0.06
     spontaneously
    -0.06
    .tele
    -0.06
    Ãłng
    -0.06
    POSITIVE LOGITS
    ä½ļåIJį
    0.08
    çļĦè§ĦåĪĻ
    0.08
    è§ĦåĪĻ
    0.08
    è¦ıåīĩ
    0.07
    è¯Ģçªį
    0.07
    æ³ķåĪĻ
    0.07
    gan
    0.07
     rule
    0.07
    åIJĮç±»
    0.07
     Regeln
    0.07
    Activations Density 0.008%

    No Known Activations