© 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. 50360
    Prev
    Next
    INDEX
    Explanations

    term or year

    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
    çļĦè®°å¿Ĩ
    -0.10
    æīĢåľ¨çļĦ
    -0.09
    人æīį
    -0.09
    èĭ±æīį
    -0.09
    Wel
    -0.09
    æīĢåľ¨åľ°
    -0.09
    æīĢåľ¨
    -0.09
    楼ä¸ĭ
    -0.09
    è®®æ¡Ī
    -0.09
    ä¸ĢåĽ¢
    -0.09
    POSITIVE LOGITS
    继ç»Ń
    0.15
    åĨįå¤ļ
    0.11
    é¢Ŀå¤ĸ
    0.11
    延伸
    0.11
    ç¹¼çºĮ
    0.11
    延éķ¿
    0.11
    åĨįä¸Ģ次
    0.10
     additional
    0.10
    åĨį次
    0.10
    æĸ°ä¸Ģè½®
    0.10
    Activations Density 0.063%

    No Known Activations