© 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. 844
    Prev
    Next
    INDEX
    Explanations

    bound for

    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
    æĭ¿åĩºæĿ¥
    -0.11
    èĥ½åģļåĪ°
    -0.10
    æĭ¿æĿ¥
    -0.09
    æ£īèĬ±
    -0.08
    ä¸į妨
    -0.08
    å¤Ł
    -0.08
    æĭ¿äºĨ
    -0.08
    å¤ĸåĽ´
    -0.08
    æĩĪ
    -0.08
    åģļä¸įåĪ°
    -0.08
    POSITIVE LOGITS
    å¼Ģå§ĭäºĨ
    0.12
    å¼Ģå§ĭ
    0.11
     begins
    0.10
    æĹ¥æŃ£å¼ı
    0.10
     begin
    0.09
    ä¸ĭä¸Ģ个
    0.09
     наÑĩина
    0.09
     Begins
    0.09
    å·²ç»ıå¼Ģå§ĭ
    0.09
    .begin
    0.09
    Activations Density 0.050%

    No Known Activations