© 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. 974
    Prev
    Next
    INDEX
    Explanations

    markers and indicators

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ration
    -0.09
    ä¸İä¼Ĺä¸įåIJĮ
    -0.09
    .Reader
    -0.09
    _flg
    -0.09
    AKE
    -0.09
    å´Ľ
    -0.08
    à¸ķรา
    -0.08
    mint
    -0.08
    oved
    -0.08
    æľĢåIJİä¸Ģ个
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.10
    篱
    0.09
    à¹Ģà¸Ńà¸ĩ
    0.09
    们
    0.09
    sWith
    0.09
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    0.09
     phrase
    0.09
    hoe
    0.09
    ä¸ªå·¥ä½ľ
    0.08
    åıŁ
    0.08
    Activations Density 0.120%

    No Known Activations