© 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. 3073
    Prev
    Next
    INDEX
    Explanations

    NFL coaches and players

    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
    igaret
    -0.10
    è¾Ł
    -0.09
    å¯ĩ
    -0.09
    æ£Ĥ
    -0.09
    æĪijéĻ¢
    -0.09
    ero
    -0.09
    缮åīįæŃ£åľ¨
    -0.09
    åĪĨ解
    -0.09
    åīIJ
    -0.09
    åĪģ
    -0.08
    POSITIVE LOGITS
    avia
    0.09
    Jur
    0.09
    енн
    0.08
    å¢ŀåĢ¼
    0.08
    è°ĸ
    0.08
    аÑĨион
    0.08
     Ragnar
    0.08
    วาà¸ĩ
    0.08
    æħĪæĤ²
    0.08
    RFC
    0.08
    Activations Density 0.021%

    No Known Activations