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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52237
    Prev
    Next
    INDEX
    Explanations

    culture and influence

    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
    éļ¾åº¦
    -0.10
    æijĨæĶ¾
    -0.09
    åĨĻåŃĹ
    -0.09
    群
    -0.09
    åIJĦèĩª
    -0.09
    åĬŀäºĭ
    -0.09
    ç§ī
    -0.09
    对ä¸ŃåĽ½
    -0.09
    ::$
    -0.09
    :disable
    -0.09
    POSITIVE LOGITS
    æĸĩåĮĸä¼łæĴŃ
    0.10
    ä¼łåªĴ
    0.10
    æĸĩåĮĸçļĦ
    0.10
    æĸĩåĮĸ交æµģ
    0.09
     Influence
    0.09
    gend
    0.09
    æĸĩåĮĸ
    0.09
    ä¾µ
    0.09
    ä¾µèļĢ
    0.09
     influences
    0.09
    Activations Density 0.102%

    No Known Activations