© 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. 16736
    Prev
    Next
    INDEX
    Explanations

    Chinese surnames

    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
    Merit
    -0.09
    轸
    -0.09
    åģ¥åħ¨
    -0.09
    åľ¨åħ¨åĽ½
    -0.08
    å¸ĪèĮĥ
    -0.08
     ан
    -0.08
    esan
    -0.08
    èIJ±
    -0.08
    秽
    -0.08
    bie
    -0.08
    POSITIVE LOGITS
    æ¹Ķ
    0.09
    inyin
    0.09
    Minor
    0.09
    è°¢è°¢ä½ł
    0.09
     Yong
    0.09
    ìĦĿ
    0.09
    icy
    0.09
     Taipei
    0.09
     Hong
    0.09
    举äºļ
    0.09
    Activations Density 0.135%

    No Known Activations