© 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. 19265
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or symbols

    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
    uern
    -0.08
    vern
    -0.08
    amenta
    -0.07
    æĺ¯ä¸Ģéģĵ
    -0.07
    ONOM
    -0.07
    кÑĢо
    -0.07
    uem
    -0.07
    iato
    -0.07
    ród
    -0.07
    æĺ¯ä¸ĢåĿĹ
    -0.07
    POSITIVE LOGITS
    (
    0.07
    imal
    0.07
    reen
    0.07
    .defaults
    0.07
    çļĦè¿ĺæĺ¯
    0.06
    äºĭäºĨ
    0.06
    æ±Ģ
    0.06
    æĪijçŃī
    0.06
    çļĦæĸ¹å¼ıæĿ¥
    0.06
    å¹Ķ
    0.06
    Activations Density 0.017%

    No Known Activations