© 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. 40188
    Prev
    Next
    INDEX
    Explanations

    illumination and shading

    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
    åĨĴ
    -0.07
    åħ³å¤´
    -0.06
    人åIJį
    -0.06
    æĹłåIJį
    -0.06
    为äºĨä¿ĿæĬ¤
    -0.06
    èĭĹ
    -0.06
     Fisch
    -0.06
    ä¿ĿæĬ¤çļĦ
    -0.06
    çļĦ身
    -0.06
    oken
    -0.06
    POSITIVE LOGITS
     specular
    0.08
    clipse
    0.08
    ISON
    0.08
    dias
    0.08
     prism
    0.08
    çijŀæĭī
    0.08
     brightest
    0.08
     crater
    0.08
    enster
    0.08
     оÑĤÑĢа
    0.08
    Activations Density 0.003%

    No Known Activations