© 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. 52453
    Prev
    Next
    INDEX
    Explanations

    latest news and features

    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
    ulton
    -0.09
    好è¿IJ
    -0.08
    ä¸įå¼Ģ
    -0.08
    ÑĪка
    -0.08
    åĬ£
    -0.08
    ussen
    -0.08
    asse
    -0.08
    çݺ
    -0.08
    æľ¬ç«Ļ
    -0.08
    perf
    -0.08
    POSITIVE LOGITS
    人们对
    0.11
    æĦı大
    0.10
    æĽĻ
    0.09
    çĶļèĩ³æĺ¯
    0.09
    è¿ľæĻ¯
    0.09
    æĬĢæľ¯åĴĮ
    0.09
    гаÑĢ
    0.09
    ä¸Ķ
    0.09
    ighter
    0.09
    hart
    0.09
    Activations Density 0.015%

    No Known Activations