© 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. 26039
    Prev
    Next
    INDEX
    Explanations

    app store or marketplace

    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
    ç»Ń
    -0.10
    è°¯
    -0.10
    olie
    -0.10
    ä¸į认è¯Ĩ
    -0.09
    etine
    -0.09
    برا
    -0.09
    æĢĻ
    -0.08
    让æ¶Īè´¹èĢħ
    -0.08
    رÙĨ
    -0.08
    å©ļ
    -0.08
    POSITIVE LOGITS
    licant
    0.09
    绵
    0.08
    .getAs
    0.08
    addin
    0.08
     tant
    0.08
    æĮ£
    0.08
    è£ĺ
    0.08
    çĻ»è®°
    0.08
    ëĭ¤
    0.08
    éĶĻè¿ĩ
    0.08
    Activations Density 0.171%

    No Known Activations