© 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. 40204
    Prev
    Next
    INDEX
    Explanations

    witnessing others or someone nearby

    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
    éĵ¸éĢł
    -0.11
    è¸ıå®ŀ
    -0.10
    ä¸İä¼Ĺä¸įåIJĮ
    -0.10
    è°¦
    -0.10
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.09
    è¸ı
    -0.09
    èĩªåľ¨
    -0.09
    åı¤ä»Ĭ
    -0.09
    å©Ĩå©Ĩ
    -0.09
    å±¥
    -0.09
    POSITIVE LOGITS
    åľ¨ä¸ĢæĹģ
    0.15
    åĽ´è§Ĥ
    0.13
     nearby
    0.11
    诧
    0.10
     bystand
    0.10
    åħ¶ä»ĸ
    0.09
    è¿ĩæĿ¥
    0.09
    åīįæĿ¥
    0.08
     witnessing
    0.08
    åħ¶ä»ĸçļĦ
    0.08
    Activations Density 0.094%

    No Known Activations