© 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. 59236
    Prev
    Next
    INDEX
    Explanations

    related 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
     Bare
    -0.09
    éĤ¯
    -0.09
     Jos
    -0.08
    ä¸İä¸ŃåĽ½
    -0.08
    ضة
    -0.08
    é¨
    -0.08
    éĿĸ
    -0.08
    æĭŁ
    -0.08
    äºĭ迹
    -0.08
    æľĢæĹ©çļĦ
    -0.08
    POSITIVE LOGITS
    Ùħات
    0.10
     Hoffman
    0.09
    顶
    0.09
    ubyte
    0.09
    宵
    0.09
    ãĥĺãĥ«
    0.09
    æķ´ä¸ªäºº
    0.09
    éĻ¢å£«
    0.09
    AXB
    0.09
    éĢį
    0.09
    Activations Density 0.072%

    No Known Activations