© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20620
    Prev
    Next
    INDEX
    Explanations

    future imports

    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
    æĿ¥èĩª
    -0.13
     ÙħÙĨÙĩا
    -0.10
    oped
    -0.10
     honor
    -0.09
     ÙħÙĨÙĩ
    -0.09
    ä»İä¸Ń
    -0.09
    ä¾Ĩèĩª
    -0.09
     from
    -0.09
    说çļĦæĺ¯
    -0.09
    ÙħÙĨ
    -0.09
    POSITIVE LOGITS
     standpoint
    0.18
    çļĦè§Ĵ度
    0.15
    æºIJ头
    0.14
     scratch
    0.13
     perspective
    0.13
    /to
    0.13
    è§Ĵ度çľĭ
    0.13
    侧éĿ¢
    0.13
     afar
    0.12
    è§Ĵ度
    0.11
    Activations Density 0.620%

    No Known Activations