© 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. 33953
    Prev
    Next
    INDEX
    Explanations

    viewpoint from afar

    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
    ساء
    -0.07
    ãģ¨ãģĨ
    -0.07
    ogs
    -0.07
    IER
    -0.07
    æĺİç¡®
    -0.07
     outstanding
    -0.07
    [__
    -0.07
    utat
    -0.07
    åĺ±åĴIJ
    -0.07
    æĺİç¡®çļĦ
    -0.06
    POSITIVE LOGITS
     outside
    0.07
    viewer
    0.07
     observers
    0.07
    èĬ¸
    0.07
     pandang
    0.07
     afar
    0.07
    elaide
    0.07
    è§Ĥå¯ŁèĢħ
    0.07
     observer
    0.07
    è§Ĥçľĭ
    0.07
    Activations Density 0.072%

    No Known Activations