© 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. 594
    Prev
    Next
    INDEX
    Explanations

    Christmas and python

    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
    wap
    -0.11
    æĬĬèĩªå·±çļĦ
    -0.09
    å½¹
    -0.09
    åºļ
    -0.08
    æ´ª
    -0.08
    éĢ
    -0.08
    å¯Łçľĭ
    -0.08
    dra
    -0.08
    西çıŃ
    -0.08
    é¢Ľ
    -0.08
    POSITIVE LOGITS
    éĢ¶
    0.10
    elves
    0.09
    kos
    0.08
    纷
    0.08
    _bot
    0.08
     Rosen
    0.08
    èĬĤ
    0.08
    ä¸ºçĽ®çļĦ
    0.08
    æŀķ
    0.08
    客æµģ
    0.08
    Activations Density 0.016%

    No Known Activations