© 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. 40388
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    ãĤ©
    -0.10
    enco
    -0.09
    åŀĤ
    -0.09
    æ´Ļ
    -0.09
    åħīåѦ
    -0.09
    秣èµģ
    -0.09
    åħ¶ä¸Ńä¸Ģ个
    -0.08
    æ°´åŁŁ
    -0.08
    å¤ļåľ°
    -0.08
    æ¸ĶèĪ¹
    -0.08
    POSITIVE LOGITS
    ä¸ŃæľŁ
    0.09
    øy
    0.09
     Äijóng
    0.08
    ness
    0.08
    comings
    0.08
    ä¸įä¸ĭ
    0.08
    boxed
    0.08
    obar
    0.08
    shire
    0.08
     highway
    0.08
    Activations Density 0.001%

    No Known Activations