© 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. 26165
    Prev
    Next
    INDEX
    Explanations

    donut/doughnut

    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
    аÑĩ
    -0.09
    oute
    -0.09
    gar
    -0.09
    .cgi
    -0.09
    éķ¿åŁİ
    -0.08
     vidé
    -0.08
    ugu
    -0.08
    çĶ¨èį¯
    -0.08
    ä¸Ńåħ³
    -0.08
    è¹ij
    -0.08
    POSITIVE LOGITS
    ðŁį©
    0.10
    é«Ģ
    0.09
    ellas
    0.09
    åĦ¿
    0.09
    -shaped
    0.09
    æŀ¢
    0.09
    ä¸ĺ
    0.09
     classics
    0.09
    说æĺ¯
    0.09
    å®ŀè´¨æĢ§
    0.08
    Activations Density 0.004%

    No Known Activations