© 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. 29651
    Prev
    Next
    INDEX
    Explanations

    seasonal changes and purchases

    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
    ä¸ĭçıŃ
    -0.10
    磾
    -0.10
    åĢĴåľ¨åľ°
    -0.09
    èĩªä¹ł
    -0.09
     بص
    -0.09
    åįĬå¤ľ
    -0.09
    ä¸ĢåĪĨéĴŁ
    -0.09
    æĻļé¥Ń
    -0.08
    å½ĵæĻļ
    -0.08
    urat
    -0.08
    POSITIVE LOGITS
    åŃ£èĬĤ
    0.17
     season
    0.14
     seasonal
    0.13
     Ñģезон
    0.13
    è¿Ļ个æŶåĢĻ
    0.12
    æĺ¥åŃ£
    0.12
    _season
    0.12
     Season
    0.12
    年度
    0.12
    èµĽåŃ£
    0.11
    Activations Density 0.277%

    No Known Activations