© 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. 57296
    Prev
    Next
    INDEX
    Explanations

    , date, or numbers

    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
    orra
    -0.08
    زÙĩ
    -0.07
     Maver
    -0.07
     maur
    -0.07
     somehow
    -0.07
    好åĥıæĺ¯
    -0.07
    ä½łæ°¸è¿ľ
    -0.07
    ose
    -0.07
    对ä¸Ĭè¿°
    -0.07
    ä¹Łæĺ¯ä¸Ģæł·
    -0.06
    POSITIVE LOGITS
    entemente
    0.07
    æĸ
    0.07
    umah
    0.06
    ROW
    0.06
    ICAS
    0.06
    лиÑĩ
    0.06
    ständ
    0.06
    yonel
    0.06
    骡
    0.06
    heit
    0.06
    Activations Density 0.001%

    No Known Activations