© 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. 60739
    Prev
    Next
    INDEX
    Explanations

    eponymous words or "e.g."

    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
    mart
    -0.10
    åı½
    -0.09
    patrick
    -0.09
    ãģĭãģ£ãģŁ
    -0.09
    labs
    -0.09
    ëĭĺ
    -0.08
    æ¯Ķå¦Ĥ
    -0.08
    ¥
    -0.08
    layer
    -0.08
    ères
    -0.08
    POSITIVE LOGITS
    elong
    0.11
    åķĸ
    0.10
    çıij
    0.10
    ither
    0.10
    æĸ¯é¡¿
    0.09
     dÃłng
    0.09
    0.09
    esty
    0.09
    ä¼ļåıijçĶŁ
    0.09
    uated
    0.09
    Activations Density 0.070%

    No Known Activations