© 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. 44355
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    obe
    -0.07
    jmp
    -0.07
    /lists
    -0.07
    raph
    -0.07
    æĪİ
    -0.07
    inston
    -0.07
    å¿ĹåĪļ
    -0.07
    åĨ°å±±
    -0.06
     berv
    -0.06
    æĪ¯
    -0.06
    POSITIVE LOGITS
    ำà¸Ļ
    0.07
    اذ
    0.07
     sane
    0.06
    çļĦä¸Ģéĥ¨åĪĨ
    0.06
    ä¿ĿçķĻ
    0.06
    ubin
    0.06
    ×ķ×IJ
    0.06
    ulé
    0.06
     sense
    0.06
     resent
    0.06
    Activations Density 0.001%

    No Known Activations