© 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. 800
    Prev
    Next
    INDEX
    Explanations

    sports games and competition

    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
    infeld
    -0.10
    åľ¨æĪijåĽ½
    -0.09
    BAB
    -0.09
    _lm
    -0.09
    oko
    -0.09
     NHL
    -0.09
    Yahoo
    -0.09
     Freund
    -0.08
     Airways
    -0.08
     Repos
    -0.08
    POSITIVE LOGITS
    åŃ¦æł¡
    0.15
    åŃ¦æł¡çļĦ
    0.14
    åħ¨åİ¿
    0.13
     girls
    0.13
    æĶ¾åѦ
    0.12
     school
    0.12
    åľ¨åŃ¦æł¡
    0.12
    女åŃ©
    0.12
     boys
    0.12
     ÑĪколÑĮ
    0.11
    Activations Density 0.110%

    No Known Activations