© 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. 26112
    Prev
    Next
    INDEX
    Explanations

    budget and finance related terms

    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
    强èĢħ
    -0.10
    ä¸įå¼Ģ
    -0.10
    å±Ĥå±Ĥ
    -0.10
    .eth
    -0.09
    ä¸įåİ»
    -0.08
    æ¶Ł
    -0.08
    ugal
    -0.08
    åįıä¼ļä¼ļåijĺ
    -0.08
    æĺ¯éĿŀ
    -0.08
     Lex
    -0.08
    POSITIVE LOGITS
    æĶ¿åºľ
    0.11
    建åĨĽ
    0.10
    ç·¨
    0.10
    è´¢æĶ¿
    0.10
    æĶ¿çŃĸ
    0.10
    鬼
    0.09
    è´¢æĶ¿éĥ¨
    0.09
    第ä¸ĢæĿ¡
    0.09
    Ø®ÙĬ
    0.09
    ç¼ĸåĪ¶
    0.09
    Activations Density 0.195%

    No Known Activations