© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27966
    Prev
    Next
    INDEX
    Explanations

    copyright or author emails

    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
    tü
    -0.11
    schritt
    -0.10
    itecture
    -0.09
    éľĨ
    -0.09
    мок
    -0.09
    ÑģпоÑģобноÑģÑĤÑĮ
    -0.09
    è¾¾æĸ¯
    -0.09
    ible
    -0.09
    à¯ģà®ķ
    -0.09
    джа
    -0.08
    POSITIVE LOGITS
    er
    0.11
    ly
    0.09
    ÑģÑĮ
    0.08
    stellung
    0.07
    u
    0.07
    a
    0.07
    st
    0.07
     же
    0.07
    atically
    0.07
    ر
    0.06
    Activations Density 0.001%

    No Known Activations