© 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. 43111
    Prev
    Next
    INDEX
    Explanations

    face and body actions

    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
    æĹłè¸ª
    -0.07
    æķĻèĤ²ç½ij
    -0.07
    oner
    -0.07
    asil
    -0.07
    汪æ´ĭ
    -0.07
     washer
    -0.07
    绾ç»İä¸įç»Ŀ
    -0.07
    евиÑĩ
    -0.06
    æĹłå¸¸
    -0.06
    asco
    -0.06
    POSITIVE LOGITS
    æĹĹä¸ĭ
    0.09
    aip
    0.07
    -flex
    0.07
     cock
    0.07
     ausgest
    0.07
    ongi
    0.07
     hÃłm
    0.07
     ÏĩαÏģακÏĦηÏģιÏĥ
    0.07
     posture
    0.07
     기ëĮĢ
    0.07
    Activations Density 0.112%

    No Known Activations