© 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. 24235
    Prev
    Next
    INDEX
    Explanations

    future, again, auctions, synthesis, Application, invention

    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
    åĨħ马
    -0.10
    转åıij
    -0.10
    åİŁæĿ¥æĺ¯
    -0.10
    å½ĵæŶ
    -0.10
    æ²¹èħ»
    -0.09
     currently
    -0.09
    ä¸ĭæ²ī
    -0.09
    åİŁæĿ¥
    -0.09
    cre
    -0.08
     mer
    -0.08
    POSITIVE LOGITS
    æĭīæĸ¯
    0.10
    æĽ´å¥½
    0.10
    æĽ´å¿«
    0.10
    주ìĿĺ
    0.10
    ä¸ĭ次
    0.10
     chú
    0.09
    æĽ´åĬł
    0.09
    æĽ´å¥½çļĦ
    0.09
    CHK
    0.09
     Chin
    0.09
    Activations Density 0.014%

    No Known Activations