© 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. 24314
    Prev
    Next
    INDEX
    Explanations

    Gospel, Easter, God, Faith

    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
    oric
    -0.09
    ÑĤай
    -0.08
    æ³Ľ
    -0.08
    å±¹
    -0.08
    éĩįçĶŁ
    -0.08
    å¤ļæĸ¹
    -0.08
    .promise
    -0.08
    ç¯Ļ
    -0.08
     Tacoma
    -0.08
    æĶĴ
    -0.08
    POSITIVE LOGITS
    æ¯ıä¸Ģ天
    0.10
     Hos
    0.10
    èĢģåŃIJ
    0.10
    Formats
    0.09
    æĹ¥å¸¸
    0.09
    éĥ¨åī¯
    0.09
    esser
    0.09
    è£ģåĪ¤
    0.08
    _BACKEND
    0.08
     Hoy
    0.08
    Activations Density 0.056%

    No Known Activations