© 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. 29425
    Prev
    Next
    INDEX
    Explanations

    as followed by clause introducer

    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
    é¦ĸåħĪæĺ¯
    -0.12
    ä»ĸ们æĺ¯
    -0.11
    èĩªä»İ
    -0.11
    å¥ł
    -0.10
    è¦ģä¹Ī
    -0.10
    好åIJĹ
    -0.10
    ä¸įä»ħæĺ¯
    -0.10
    æľīä»·åĢ¼
    -0.10
    èµĦ
    -0.09
    ä»ĸæĺ¯ä¸Ģ个
    -0.09
    POSITIVE LOGITS
    semble
    0.12
    äºĨè§£æĽ´å¤ļ
    0.10
    ç´§
    0.09
    unc
    0.09
    å¤ļå¹´çļĦ
    0.09
    åīįéĿ¢
    0.09
    çľĭæĿ¥
    0.08
    bury
    0.08
    æĮīä¸ĭ
    0.08
    ç»ıéªĮ
    0.08
    Activations Density 0.046%

    No Known Activations