© 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. 60942
    Prev
    Next
    INDEX
    Explanations

    university name abbreviations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    juan
    -0.10
    ä¹ĺåĿIJ
    -0.08
     Parliamentary
    -0.08
    ัว
    -0.08
    ä¸ĸçķĮä¸Ĭ
    -0.08
    ä¼ij
    -0.08
    çľģæķĻèĤ²åİħ
    -0.08
    éĻ·éĺ±
    -0.08
    润
    -0.08
    大éĿ¢ç§¯
    -0.08
    POSITIVE LOGITS
    .edu
    0.11
    -educated
    0.10
    éĻĦå±ŀ
    0.10
    åĮ»åѦéĻ¢
    0.10
    -aff
    0.09
    ë°ķ
    0.09
     sweat
    0.09
    éĻĦè¿ijçļĦ
    0.09
    quare
    0.08
    æªIJ
    0.08
    Activations Density 0.083%

    No Known Activations