© 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. 59278
    Prev
    Next
    INDEX
    Explanations

    families and groups

    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
    æĪIJ为ä¸ĢåIJį
    -0.10
    åıĮéĩį
    -0.10
    åĭŁ
    -0.09
    Fight
    -0.09
    DOUBLE
    -0.09
    åĪ¶æĪIJ
    -0.08
    ä¸įåŃĺåľ¨
    -0.08
     NotImplemented
    -0.08
    çĶŁæ´»ä¸Ń
    -0.08
    æĬĬè¿ĻäºĽ
    -0.08
    POSITIVE LOGITS
    pit
    0.10
    éĢ£ãĤĮ
    0.10
     lẫn
    0.10
    åIJĮè¡Į
    0.10
    åıĭ好
    0.09
     PIT
    0.09
    æĢİä¹ĪåĬŀ
    0.09
     pit
    0.09
    groupId
    0.09
    Kr
    0.09
    Activations Density 0.045%

    No Known Activations