© 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. 26548
    Prev
    Next
    INDEX
    Explanations

    marks that start a phrase or sentence

    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
    ãģ¾ãģĻãģĮ
    -0.10
    èİ«åIJį
    -0.09
     wholes
    -0.09
    é©¿ç«Ļ
    -0.09
    çİ°éĺ¶æ®µ
    -0.09
    èļģ
    -0.08
    (es
    -0.08
    åįļæĸĩ
    -0.08
    .SelectedItems
    -0.08
    档次
    -0.08
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.16
     воÑĤ
    0.13
    æĪĸèĢħ说
    0.12
    æ¯Ķå¦Ĥ说
    0.11
    ä½łçľĭ
    0.11
    è¿ĩç¨ĭå½ĵä¸Ń
    0.10
    è¿Ļæł·ä¸Ģ个
    0.10
    ãģ£ãģ¦ãģĦãģĨ
    0.10
    éĿŀ常çļĦ
    0.10
     ê·¸ëŁ¬ëĭĪê¹Į
    0.10
    Activations Density 0.076%

    No Known Activations