© 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. 55717
    Prev
    Next
    INDEX
    Explanations

    fasteners and mechanical components

    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
    ç«Ļç«ĭ
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    åĬ¨åĬĽ
    -0.09
    /manual
    -0.09
    ç«Ļåľ¨
    -0.09
    ç«ĻçĿĢ
    -0.09
    ç«Ļ
    -0.09
    íĭĢ
    -0.09
     deadlock
    -0.08
    鬣
    -0.08
    POSITIVE LOGITS
     nut
    0.09
    æĦļ
    0.09
    涨
    0.09
    æį£
    0.09
    夯
    0.09
    athing
    0.08
    æĿ¯
    0.08
    æºı
    0.08
    ä½ıæīĢ
    0.08
    åŀ«
    0.08
    Activations Density 0.094%

    No Known Activations