© 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. 40337
    Prev
    Next
    INDEX
    Explanations

    next level, complete missions

    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
    åĸĭ
    -0.11
    gend
    -0.10
    ä¸įèµ·
    -0.10
    åı¯éĿłçļĦ
    -0.10
    åı¯éĿłæĢ§
    -0.10
    åĢ¦
    -0.10
    åı¯éĿł
    -0.09
    æłĩ
    -0.09
    å®ŀæĥł
    -0.09
    ussy
    -0.09
    POSITIVE LOGITS
    解éĶģ
    0.13
    éļ¾åº¦
    0.11
    解å¼Ģ
    0.11
    éĢļåħ³
    0.10
    æĮijæĪĺ
    0.10
    éĹ¯
    0.10
    éļ¾é¢ĺ
    0.09
    åĽ°éļ¾
    0.09
    è°ľ
    0.09
     missions
    0.09
    Activations Density 0.282%

    No Known Activations