© 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. 40259
    Prev
    Next
    INDEX
    Explanations

    verify user credentials

    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
    åľ¯
    -0.10
    неÑĨ
    -0.10
    棰
    -0.09
    nown
    -0.09
    èĭ¥æľī
    -0.09
    å¿Į
    -0.09
    æ²ĸ
    -0.09
    ç¼Ł
    -0.09
    楫
    -0.09
     Travis
    -0.09
    POSITIVE LOGITS
    说æ³ķ
    0.10
    身份
    0.10
    ä¸Ģçķª
    0.09
     maté
    0.09
    说çļĦæĺ¯
    0.09
    9
    0.09
    æľīæķĪæĢ§
    0.09
    å±ŀå®ŀ
    0.09
    4
    0.09
     existence
    0.09
    Activations Density 0.242%

    No Known Activations