© 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. 16691
    Prev
    Next
    INDEX
    Explanations

    DTD PL

    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
    éĢģæĿ¥
    -0.08
    (getClass
    -0.08
    itto
    -0.07
     [...]
    -0.07
    æijĨåľ¨
    -0.07
     [âĢ¦]
    -0.07
    âĢŁ
    -0.06
    æĿ¥ä¸´
    -0.06
    tı
    -0.06
     Chrom
    -0.06
    POSITIVE LOGITS
    ë²Į
    0.11
     дополниÑĤелÑĮно
    0.10
    æŁIJäºĽ
    0.09
    ä»įæľī
    0.09
    æĸĩç«łæĿ¥æºIJ
    0.09
    åIJįåŃĹ
    0.09
    è¿ĺæľīä¸ĢäºĽ
    0.09
    éĺIJ
    0.09
    å°ıåŀĭ
    0.08
     ìĦ
    0.08
    Activations Density 2.414%

    No Known Activations