© 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. 16636
    Prev
    Next
    INDEX
    Explanations

    proper nouns from various languages

    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
    éļıä¹ĭ
    -0.09
    ania
    -0.09
    vig
    -0.08
    alez
    -0.08
    åIJİèĢħ
    -0.08
     bay
    -0.08
    плаÑĤ
    -0.08
    ony
    -0.08
    ulations
    -0.07
    \Form
    -0.07
    POSITIVE LOGITS
     Hann
    0.10
    æĿŁ
    0.09
    ä¹ĭç±»çļĦ
    0.09
    缩
    0.09
    åIJ¬äºĨ
    0.08
    çŃīæĸ¹éĿ¢çļĦ
    0.08
    諸
    0.08
    çŃīæĸ¹éĿ¢
    0.08
    èĤĨ
    0.08
    èĹģ
    0.08
    Activations Density 0.084%

    No Known Activations