© 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. 16629
    Prev
    Next
    INDEX
    Explanations

    weeks or calendar dates

    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
    æĻļä¸Ĭ
    -0.11
    å¤ľéĹ´
    -0.11
     ноÑĩ
    -0.10
    isko
    -0.10
    èµ·æĿ¥
    -0.10
    å¤ľéĩĮ
    -0.09
    baugh
    -0.09
    виз
    -0.09
     nighttime
    -0.09
    解å¼Ģ
    -0.09
    POSITIVE LOGITS
    æľ¬åij¨
    0.11
    ä¸Ĭåij¨
    0.10
    ä¸ĭåij¨
    0.10
    秫
    0.10
    æ¯ıåij¨
    0.10
    åij¨
    0.09
    羣æŃ£
    0.09
    æݸ
    0.09
    æĽ·
    0.09
    æ¡£
    0.09
    Activations Density 0.261%

    No Known Activations