© 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. 666
    Prev
    Next
    INDEX
    Explanations

    shape and geometry

    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
     positivity
    -0.08
     зак
    -0.07
    ç»Ŀ对
    -0.07
     comparative
    -0.06
     deferred
    -0.06
     Sugar
    -0.06
    ibus
    -0.06
     positive
    -0.06
    les
    -0.06
    触
    -0.06
    POSITIVE LOGITS
    沿çĿĢ
    0.09
     perpendicular
    0.08
     Sertif
    0.08
    á»ıng
    0.08
     cylindrical
    0.08
    slice
    0.08
     excer
    0.08
    ãģ«æ²¿
    0.08
    ×ķר×ļ
    0.08
    éĿ¢ç§¯çļĦ
    0.08
    Activations Density 0.002%

    No Known Activations