© 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. 60951
    Prev
    Next
    INDEX
    Explanations

    facial expression and recognition

    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
    尾巴
    -0.08
    ald
    -0.08
     Terd
    -0.08
    èĦļ趾
    -0.08
    ëķħ
    -0.07
    vestir
    -0.07
    æĮĩå®ļåľ°çĤ¹
    -0.07
    ä½łä¸Ģ个
    -0.07
    ãģ£ãģ½
    -0.07
    澡
    -0.07
    POSITIVE LOGITS
    -face
    0.15
     faces
    0.13
    (face
    0.13
     лиÑĨа
    0.12
    éĿ¢çļĦ
    0.12
     facial
    0.12
     Face
    0.12
    éĿ¢
    0.12
    -faced
    0.12
     face
    0.12
    Activations Density 0.105%

    No Known Activations