© 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. 4786
    Prev
    Next
    INDEX
    Explanations

    estimation

    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
    sek
    -0.09
    parsers
    -0.08
    anzi
    -0.08
     Grosso
    -0.08
    ÏĦηÏĥη
    -0.07
     اÙĦسر
    -0.07
    ArrayOf
    -0.07
    çļĦä¸Ģ大
    -0.07
     sond
    -0.07
    aturen
    -0.07
    POSITIVE LOGITS
     component
    0.09
     portion
    0.09
     components
    0.09
    è¿Ļéĥ¨åĪĨ
    0.09
     Anteil
    0.08
    æĪIJåĪĨ
    0.08
    æĪIJ份
    0.08
    åĴĮéĿŀ
    0.08
     ÑģоÑģÑĤавлÑı
    0.08
     part
    0.08
    Activations Density 0.022%

    No Known Activations