© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11446
    Prev
    Next
    INDEX
    Explanations

    example or prime instance

    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
    涵
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    éĽĦ
    -0.08
    ä¾Ĩèĩª
    -0.08
    åı¯ä»¥èİ·å¾Ĺ
    -0.08
     ÑĥÑĢовнÑı
    -0.08
    .rar
    -0.08
    ç´§å¼ł
    -0.08
    åĴ³
    -0.08
    ä¸įä»ħåı¯ä»¥
    -0.08
    POSITIVE LOGITS
    ä¾ĭåŃIJ
    0.22
    çļĦä¾ĭåŃIJ
    0.20
    为ä¾ĭ
    0.19
     example
    0.18
    ä¾ĭ
    0.17
     exemplo
    0.16
    举ä¾ĭ
    0.16
     examples
    0.15
     пÑĢимеÑĢ
    0.15
    example
    0.15
    Activations Density 0.068%

    No Known Activations