© 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. 18972
    Prev
    Next
    INDEX
    Explanations

    warriors, women, and heroic figures

    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
    ophobia
    -0.09
    档次
    -0.08
    罨
    -0.08
    çĵ·
    -0.08
    æĻļä¼ļ
    -0.08
    é¼ĭ
    -0.08
     Bunny
    -0.08
    æĿĤå¿Ĺ
    -0.07
    积水
    -0.07
     Jam
    -0.07
    POSITIVE LOGITS
    æŃ¦æľ¯
    0.19
    èĭ±åĭĩ
    0.18
    èĭ±éĽĦ
    0.16
    åĨĽäºĭ
    0.15
    éĵł
    0.15
    æŃ¦ä¾ł
    0.15
    åĭĩ士
    0.15
    æĪĺæĸĹ
    0.15
    éªģ
    0.14
    æīĵä»Ĺ
    0.14
    Activations Density 0.106%

    No Known Activations