© 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. 11321
    Prev
    Next
    INDEX
    Explanations

    similarly / same / origin

    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
    æĹłè®ºæĺ¯
    -0.10
    ä¸Ģæĸ¹éĿ¢
    -0.10
     Husband
    -0.09
    æĹłè®º
    -0.09
    èĬ«
    -0.09
    iggs
    -0.09
    _combined
    -0.09
    æľįåĭĻæĪĸ
    -0.09
    æľ¬ç«Ļ
    -0.09
    ä¸įåĥı
    -0.09
    POSITIVE LOGITS
    类似çļĦ
    0.17
     similarly
    0.14
    åIJĮæł·æĺ¯
    0.14
    åIJĮæł·
    0.13
    åIJĮæł·çļĦ
    0.13
    åIJĮ樣
    0.13
     same
    0.11
    类似
    0.11
    ä¹ŁåIJĮæł·
    0.11
    ä¸Ģæł·çļĦ
    0.10
    Activations Density 0.105%

    No Known Activations