© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20010
    Prev
    Next
    INDEX
    Explanations

    whose questions

    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
    家ä¼Ļ
    -0.10
    äºĭçī©
    -0.09
    things
    -0.09
    europ
    -0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.09
    人士
    -0.08
    çªĹå¸ĺ
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    åģļäºĭ
    -0.08
    ariat
    -0.08
    POSITIVE LOGITS
    æľīèī²
    0.11
    даÑĩи
    0.08
    ç§įç±»
    0.08
    ../../../../
    0.08
    çļĦæĹ¶ä»£
    0.08
     whose
    0.08
    Fallback
    0.08
     trá»Ŀi
    0.08
    HeaderCode
    0.08
     Owners
    0.08
    Activations Density 0.932%

    No Known Activations