© 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. 64669
    Prev
    Next
    INDEX
    Explanations

    art and related topics

    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
     geopol
    -0.09
    culp
    -0.09
    ignano
    -0.09
     spectac
    -0.09
     доÑģÑĤовеÑĢ
    -0.09
     fakta
    -0.09
    üter
    -0.08
    /photo
    -0.08
    ioxide
    -0.08
    _errno
    -0.08
    POSITIVE LOGITS
    æĬ½è±¡
    0.09
    强è°ĥäºĨ
    0.08
    强è°ĥ
    0.08
    æĸ¹æ³ķ论
    0.08
    æıIJåĢ¡
    0.08
     practice
    0.07
    è¿Ļç§įåģļæ³ķ
    0.07
     conceptual
    0.07
     abstraction
    0.07
     emphasizing
    0.07
    Activations Density 0.305%

    No Known Activations