© 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. 20987
    Prev
    Next
    INDEX
    Explanations

    hard work, grinding, working

    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
    鬲
    -0.11
    解说
    -0.10
    ä¹ŀ
    -0.09
    ä¼Ļ
    -0.09
    å§Ķ
    -0.09
    åī¡
    -0.09
    å¾®å¦Ļ
    -0.09
    æĶ¾åĩº
    -0.09
    _SUITE
    -0.09
    澳大
    -0.08
    POSITIVE LOGITS
    åĭ¤å¥ĭ
    0.13
    æķ¬ä¸ļ
    0.10
    è¸ıå®ŀ
    0.09
    åĭ¤åĬ³
    0.09
    ä¸įåĬ¨
    0.09
    æĢģ度
    0.09
    è¯ļä¿¡
    0.09
    åĭ¤
    0.09
    èµ·æĿ¥
    0.09
    è®¤çľŁåŃ¦ä¹ł
    0.09
    Activations Density 0.017%

    No Known Activations