© 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. 21790
    Prev
    Next
    INDEX
    Explanations

    in many ways

    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
    è¡·
    -0.10
    ä¸ĩä¸Ģ
    -0.09
    æľīä¸Ģ天
    -0.09
    æģģ
    -0.08
    å»ī
    -0.08
    æīĢåľ¨çļĦ
    -0.08
    pei
    -0.08
    QtCore
    -0.08
    ellan
    -0.08
     TCL
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Łæĺ¯
    0.12
    è¿Ļæĺ¯æĪij
    0.12
    è¿Ļå°±æĺ¯
    0.11
    æīĵå¼ĢäºĨ
    0.11
    è¿Ļæĺ¯ä¸Ģ个
    0.11
    åı¯ä»¥è¯´
    0.11
    è¿Ļæĺ¯
    0.10
    è¿Ļæĺ¯æĪij们
    0.10
    æĦıä¹īä¸Ĭ
    0.10
    人人
    0.10
    Activations Density 0.024%

    No Known Activations