© 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. 7824
    Prev
    Next
    INDEX
    Explanations

    anteromedial, posteromedial, dorsal, anterior

    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
    èĥĮåIJİçļĦ
    -0.07
    ä¸Ģæł·çļĦ
    -0.07
    kins
    -0.07
    uld
    -0.07
    è¿Ļ让
    -0.06
    -0.06
    stwo
    -0.06
    ables
    -0.06
    ers
    -0.06
    able
    -0.06
    POSITIVE LOGITS
    wärts
    0.10
    most
    0.10
    Ñģполни
    0.10
    mente
    0.09
    inux
    0.09
    -most
    0.09
    .Factory
    0.09
    æĸ¹çķ¥
    0.09
    ized
    0.09
    ALLY
    0.08
    Activations Density 0.051%

    No Known Activations