© 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. 837
    Prev
    Next
    INDEX
    Explanations

    comparisons after 'to'

    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
    欢ä¹IJ
    -0.10
    表éĿ¢ä¸Ĭ
    -0.09
    æľºç¥¨
    -0.09
    椿
    -0.09
    æĻļæĬ¥
    -0.09
    çľĭèµ·æĿ¥
    -0.09
    çĶ¸
    -0.09
    çľĭä¼¼
    -0.09
    oste
    -0.08
    cxx
    -0.08
    POSITIVE LOGITS
    IgnoreCase
    0.12
    ãĤĦãģ£ãģ±ãĤĬ
    0.10
    WISE
    0.10
    æĺ¯ä¸Ģéĥ¨
    0.10
    енд
    0.10
     unfavor
    0.09
    èĭĩ
    0.09
    favor
    0.09
     favor
    0.08
    强大
    0.08
    Activations Density 0.025%

    No Known Activations