© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15031
    Prev
    Next
    INDEX
    Explanations

    facial expressions or sensory perception

    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
    缸æĢĿ
    -0.08
    èĥ¡æĢĿ
    -0.08
    _BGR
    -0.07
    声åIJį
    -0.07
    èħ¥
    -0.07
    壮è§Ĥ
    -0.07
    æĢĴåIJ¼
    -0.07
    aggregate
    -0.07
    ertime
    -0.07
    Sock
    -0.07
    POSITIVE LOGITS
    æµģéľ²åĩº
    0.09
    åľ¨èĦ¸ä¸Ĭ
    0.08
    ä¸Ģä¸Ŀ
    0.08
    wan
    0.08
     wan
    0.07
    æĺİæĺ¾çļĦ
    0.07
    æĺİæĺ¾
    0.07
    ä¸ĢåĪĨ
    0.07
     expression
    0.07
    表æĥħ
    0.07
    Activations Density 0.069%

    No Known Activations