© 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. 64008
    Prev
    Next
    INDEX
    Explanations

    Prophet Muhammad, Google Scholar publications

    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
    çŁ¾
    -0.10
    缼å¼Ģ
    -0.09
    èĭ±æł¼
    -0.09
     Barton
    -0.09
    æı©
    -0.09
    eg
    -0.09
    ä½ĵçİ°åľ¨
    -0.09
    çĿ¬
    -0.08
    éļ¾åħ³
    -0.08
    å½ĵåľ°æĶ¿åºľ
    -0.08
    POSITIVE LOGITS
    è½½
    0.10
    à¹Ģà¸ĸ
    0.09
     Pey
    0.09
    iero
    0.09
    åĺī
    0.09
    好æ¶Īæģ¯
    0.08
    å·´å·´
    0.08
    okit
    0.08
    çķĶ
    0.08
    åĿij
    0.08
    Activations Density 0.051%

    No Known Activations