© 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. 665
    Prev
    Next
    INDEX
    Explanations

    signed deals, attention, noticed

    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
    éĢŀ
    -0.10
    Ñģон
    -0.10
    ä¹Łä¸įæĥ³
    -0.09
    ä»ĩ
    -0.09
    _checkout
    -0.09
    ç»Łè®¡å±Ģ
    -0.09
    éĥ½åĸľæ¬¢
    -0.08
    åºŀ大
    -0.08
    åĩłåįģå¹´
    -0.08
    pulse
    -0.08
    POSITIVE LOGITS
    主æµģ
    0.11
    æľºä¼ļ
    0.09
    åľ°æĸ¹æĶ¿åºľ
    0.09
    éĹ»åIJį
    0.09
    éķģ
    0.09
    ä¸ĸ人
    0.09
    æľīåIJį
    0.09
     ìĿ¸ìłķ
    0.09
    æĬĢæľ¯çłĶåıij
    0.09
    æľºéģĩ
    0.09
    Activations Density 0.085%

    No Known Activations