© 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. 59411
    Prev
    Next
    INDEX
    Explanations

    was / were followed by past participles

    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
    æĢİä¹Īçľĭ
    -0.10
    ä»ĭ
    -0.10
    髯
    -0.09
    wd
    -0.09
    æĹĹä¸ĭ
    -0.09
    Ñīе
    -0.09
    æĸĹ
    -0.08
    WD
    -0.08
    åı¸
    -0.08
    âĪ
    -0.08
    POSITIVE LOGITS
    åĽłä¸ºä»ĸ们
    0.11
    满满
    0.11
    æĮĩåIJij
    0.10
    åģľçķĻåľ¨
    0.09
    æĴĻ
    0.09
    èĴ¸
    0.09
    迸
    0.09
    åģ¾
    0.09
     пÑĥнк
    0.09
    asco
    0.09
    Activations Density 0.110%

    No Known Activations