© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29735
    Prev
    Next
    INDEX
    Explanations

    gestures and hand signals

    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
    ä¸ĢåĪ»
    -0.10
    å¡«
    -0.09
    夤
    -0.09
    arry
    -0.09
    .cz
    -0.09
    blings
    -0.09
    ä¹Łå¸ĮæľĽ
    -0.09
    âĹĪ
    -0.08
    .ny
    -0.08
    ç»ıèIJ¥
    -0.08
    POSITIVE LOGITS
    æīĭåĬ¿
    0.23
     gesture
    0.14
     gestures
    0.14
    gest
    0.12
     gest
    0.12
     Gest
    0.11
    gesture
    0.11
     thumb
    0.10
    姿åĬ¿
    0.10
    æīĭæİĮ
    0.10
    Activations Density 0.045%

    No Known Activations