© 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. 3019
    Prev
    Next
    INDEX
    Explanations

    all aspects

    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
    permalink
    -0.08
    rok
    -0.08
    æĿ
    -0.08
    ToWorld
    -0.08
    repid
    -0.08
    fmt
    -0.08
     erm
    -0.08
    é©·
    -0.08
    ework
    -0.08
    hai
    -0.08
    POSITIVE LOGITS
     aspects
    0.28
     aspect
    0.24
    æĸ¹éĿ¢
    0.23
    aspect
    0.19
    æĸ¹éĿ¢çļĦ
    0.19
    _aspect
    0.18
    åIJĦ个æĸ¹éĿ¢
    0.18
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.17
    ä¸ī个æĸ¹éĿ¢
    0.17
     Aspect
    0.17
    Activations Density 0.052%

    No Known Activations