© 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. 15410
    Prev
    Next
    INDEX
    Explanations

    structured data formatting

    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
    s
    -0.12
    scape
    -0.10
    ìĿĺ
    -0.10
    ered
    -0.09
    abouts
    -0.09
    tte
    -0.09
    çļĦè¿ĩç¨ĭä¸Ń
    -0.09
    sider
    -0.09
    erior
    -0.09
    sWith
    -0.08
    POSITIVE LOGITS
    åľ¨
    0.10
    Ùĩ
    0.10
    ´
    0.09
    èĩªå·±
    0.08
    ìį¨
    0.08
    ção
    0.08
    ãģĵãģ¨
    0.07
    ê¹IJ
    0.07
    os
    0.07
    åľ¨çľĭåĪ°
    0.07
    Activations Density 0.003%

    No Known Activations