© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34527
    Prev
    Next
    INDEX
    Explanations

    face recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èħ¿
    -0.11
    ç³»
    -0.10
    éĵº
    -0.10
    ebra
    -0.10
    èĪįä¸įå¾Ĺ
    -0.09
    æľīæľĽ
    -0.09
    èħ¹
    -0.09
    è¸Ŀ
    -0.09
    æīĭèħķ
    -0.09
    è¯Ŀé¢ĺ
    -0.09
    POSITIVE LOGITS
    éĿ¢éĥ¨
    0.20
     facial
    0.17
    éĿ¢åħ·
    0.17
     Facial
    0.17
     Face
    0.16
    表æĥħ
    0.16
    çļĦèĦ¸
    0.16
     face
    0.15
    çļĦ表æĥħ
    0.15
    Face
    0.14
    Activations Density 0.108%

    No Known Activations