© 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. 51732
    Prev
    Next
    INDEX
    Explanations

    describing styles and attributes

    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
    ÑĢабоÑĤка
    -0.09
    iance
    -0.08
    shire
    -0.08
    è®¤çľŁåŃ¦ä¹ł
    -0.08
    å·¥ä½ľèĢħ
    -0.08
    åľ¨æĦı
    -0.08
    OLON
    -0.08
    odon
    -0.08
    heim
    -0.08
    座ä½į
    -0.08
    POSITIVE LOGITS
    çijĽ
    0.11
    ãģĭãģ¤
    0.11
    çļĦå½¢å¼ı
    0.11
     yet
    0.11
    èĢĮåıĪ
    0.10
    çļĦæĸ¹å¼ıæĿ¥
    0.10
    家éķ¿ä»¬
    0.09
    åĽłä¸ºå®ĥ
    0.09
    ä¸Ģå¹ķ
    0.09
    ìłģìĿ´
    0.09
    Activations Density 0.211%

    No Known Activations