© 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. 616
    Prev
    Next
    INDEX
    Explanations

    recipe / recipes

    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
    itarian
    -0.10
    ordion
    -0.09
    æģŃæķ¬
    -0.09
    çľĭçĤ¹
    -0.09
    åIJĥé¥Ń
    -0.09
     Hoe
    -0.09
    bull
    -0.08
    å¼Ģçİ©ç¬ij
    -0.08
    ç§Ĩ
    -0.08
    ä¸Ģ个å°ı
    -0.08
    POSITIVE LOGITS
     recipe
    0.17
     recipes
    0.16
    éħįæĸ¹
    0.15
     formula
    0.12
     Recipes
    0.12
     ÑĢеÑĨеп
    0.12
     Recipe
    0.11
    recipes
    0.11
    recipe
    0.11
    Recipes
    0.11
    Activations Density 0.093%

    No Known Activations