© 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. 40228
    Prev
    Next
    INDEX
    Explanations

    religious preaching or sermon series

    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
    顺
    -0.10
    rens
    -0.09
    èĪĨ
    -0.09
    礼è²Į
    -0.08
    anje
    -0.08
    æĭ¥
    -0.08
    ç»´å°Ķ
    -0.08
     Rit
    -0.08
    寻
    -0.08
    Shot
    -0.08
    POSITIVE LOGITS
    讲课
    0.12
    æ¼Ķ讲
    0.11
    è¬Ľ
    0.10
    æ»Ķ
    0.10
    讲
    0.10
    éŀŃ
    0.10
     preached
    0.10
    çijĽ
    0.10
    讲解
    0.10
    çıĤ
    0.10
    Activations Density 0.026%

    No Known Activations