© 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. 16804
    Prev
    Next
    INDEX
    Explanations

    without words following

    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
    è¦ģä¸įçĦ¶
    -0.10
    ä¸įåIJĮç±»åŀĭ
    -0.10
    ä¸įæŃ¢
    -0.10
    æĺİçĻ½äºĨ
    -0.10
    åĤįæĻļ
    -0.09
    é»Ħæĺı
    -0.09
    西äºļ
    -0.09
    ä¸įå¿į
    -0.09
    ä¸įåĨį
    -0.09
    .Sql
    -0.09
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.11
     necessarily
    0.11
    abox
    0.10
    åį´åıĪ
    0.10
     há»ģ
    0.10
    ä¸Ŀ毫
    0.10
    /on
    0.09
     impunity
    0.09
    èĻŀ
    0.09
     mention
    0.09
    Activations Density 0.063%

    No Known Activations