© 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. 55219
    Prev
    Next
    INDEX
    Explanations

    showing fractions

    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
    ä¸İ伦
    -0.06
    å¼Ł
    -0.06
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.06
    å¥Īä½ķ
    -0.06
    uil
    -0.06
    æķ¬ä¸ļç²¾ç¥ŀ
    -0.06
    软硬
    -0.06
     dessus
    -0.06
    ponder
    -0.06
    å¿ĥçIJĨåİĭåĬĽ
    -0.06
    POSITIVE LOGITS
    ugi
    0.08
    idler
    0.08
    peon
    0.07
    wald
    0.07
    CurrentValue
    0.07
    htag
    0.07
    é¢ĸ
    0.07
    enga
    0.07
    urus
    0.07
    ç«ĭåĪ»
    0.06
    Activations Density 0.002%

    No Known Activations