© 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. 38294
    Prev
    Next
    INDEX
    Explanations

    time and speed

    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
     Marsh
    -0.09
    تÙĬ
    -0.09
    ÑĪÑĥ
    -0.09
    æIJ¶
    -0.09
    鸣
    -0.09
    äºĶéĩij
    -0.08
    ä¼Ļ
    -0.08
    å·²ç»ıæĺ¯
    -0.08
    æĭĻ
    -0.08
    æŀ¥
    -0.08
    POSITIVE LOGITS
    æĪIJåŀĭ
    0.09
    é»ijé¾Ļ
    0.09
    EventListener
    0.09
    赦
    0.09
    å¼Ģå±Ģ
    0.09
    å¼Ģä¸ļ
    0.08
    æĪIJ为ä¸ŃåĽ½
    0.08
    sek
    0.08
    éĿ¢è²Į
    0.08
    åıªéľĢ
    0.08
    Activations Density 0.049%

    No Known Activations