© 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. 24091
    Prev
    Next
    INDEX
    Explanations

    sorting by date, string, score

    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
    åŀĤ
    -0.10
    é«ĺå³°æľŁ
    -0.09
    æ¯Ķäºļ
    -0.09
    atial
    -0.09
    åŃIJå¼¹
    -0.08
    ä¸İåħ¶
    -0.08
    æ·±åĪ»çļĦ
    -0.08
    æİ¥åĬĽ
    -0.08
    åIJ¯åĬ¨ä»ªå¼ı
    -0.08
    rine
    -0.08
    POSITIVE LOGITS
    edList
    0.10
    enance
    0.09
    -by
    0.09
    éĵĤ
    0.09
    æİĴåºı
    0.09
    æİĴåĪĹ
    0.09
    å½°
    0.09
    æĮī
    0.09
    ofi
    0.09
     soo
    0.09
    Activations Density 0.178%

    No Known Activations