© 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. 64023
    Prev
    Next
    INDEX
    Explanations

    factor of N or order of magnitude

    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
    æ¸IJ
    -0.10
     sag
    -0.09
    å¤ĸ交
    -0.08
     Dipl
    -0.08
    æ´ĭ
    -0.08
    gang
    -0.08
    .over
    -0.07
     rem
    -0.07
    èIJ¥åķĨ
    -0.07
     Gang
    -0.07
    POSITIVE LOGITS
    åĢį
    0.14
     gấp
    0.12
    å¾Ĺå¤ļ
    0.11
    orders
    0.11
    åĩłæ¬¡
    0.11
    æķ°åįģ
    0.10
     vezes
    0.10
    illard
    0.10
    å¦Ĥæŀľè¯´
    0.10
     times
    0.10
    Activations Density 0.111%

    No Known Activations