© 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. 9067
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
    æĽ´å¤ļ
    -0.11
    æĽ´å¤ļä¿¡æģ¯
    -0.11
    èĴ¿
    -0.10
     WARRANTY
    -0.10
    ä¹Łæĺ¯å¦ĤæѤ
    -0.09
    леÑĢ
    -0.09
    ä¹Łä¸į
    -0.09
    ä»İä¸Ń
    -0.09
    âĺ°
    -0.09
    诰
    -0.09
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.09
    elin
    0.08
    клон
    0.08
    讫
    0.08
    éĶľ
    0.07
    rossover
    0.07
    ä¸Ģæł·çļĦ
    0.07
    âĸ¹
    0.07
     boat
    0.07
    ROL
    0.07
    Activations Density 0.203%

    No Known Activations