© 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. 34792
    Prev
    Next
    INDEX
    Explanations

    free download or book

    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
    etz
    -0.07
    otron
    -0.07
    êté
    -0.07
    è¿ľ
    -0.07
    arella
    -0.07
    èij¡
    -0.07
    è¿ĻæŶçļĦ
    -0.07
    ey
    -0.07
    ä¸Ģå¿ĥ
    -0.07
    arris
    -0.07
    POSITIVE LOGITS
    æĪIJèĢĥ
    0.07
    acre
    0.07
    æĥķ
    0.07
    iman
    0.06
    indle
    0.06
    rhs
    0.06
    婧
    0.06
     sav
    0.06
     wake
    0.06
    åĬŁ
    0.06
    Activations Density 0.059%

    No Known Activations