© 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. 29451
    Prev
    Next
    INDEX
    Explanations

    fitness and wellness

    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
    Negative Logits
    ç¥Ń
    -0.09
     Elections
    -0.08
     elections
    -0.08
    è¿Ļ个è¯į
    -0.08
    è¾Ľ
    -0.08
    ä¸ĸçķĮä¸Ĭ
    -0.08
     chuyến
    -0.08
    åĽ¢åľĨ
    -0.08
    ç¼Ģ
    -0.08
    ä¿Ŀå¯Ĩ
    -0.08
    POSITIVE LOGITS
    åĻ¨æ¢°
    0.17
    åģ¥èº«æĪ¿
    0.16
    æķĻç»ĥ
    0.15
    åģ¥èº«
    0.15
     fitness
    0.14
    çijľä¼½
    0.13
    åĻ¨æĿIJ
    0.13
     Fitness
    0.12
    åħ¨æ°ijåģ¥èº«
    0.12
     gym
    0.12
    Activations Density 0.302%

    No Known Activations