© 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. 63902
    Prev
    Next
    INDEX
    Explanations

    in this case

    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
    æĸ¹éĿ¢çļĦ
    -0.11
    æĸ¹éĿ¢
    -0.10
    çħ§äº®
    -0.10
    æIJŀå®ļ
    -0.09
    ä¸Ģ身
    -0.09
    ä¹ĭ声
    -0.09
    åľ¨è¿Ļ
    -0.09
    æĮŁ
    -0.09
    -gap
    -0.09
     vign
    -0.08
    POSITIVE LOGITS
    举
    0.09
     ÑģамÑĭй
    0.09
    LineNumber
    0.09
    à¹ģหละ
    0.08
    壹
    0.08
    壤
    0.08
    wor
    0.08
    รว
    0.08
    滨
    0.08
    .MAIN
    0.08
    Activations Density 0.032%

    No Known Activations