© 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. 37220
    Prev
    Next
    INDEX
    Explanations

    organize events

    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
    第ä¸Ģ天
    -0.10
    çIJIJ
    -0.09
    ead
    -0.09
    outu
    -0.09
    bai
    -0.09
    ä¸įçĶ¨
    -0.09
     Sour
    -0.08
    SUPER
    -0.08
    æĮĩæĮ¥
    -0.08
    ulos
    -0.08
    POSITIVE LOGITS
    ä¸įå®ļ
    0.13
    èĬĤåģĩæĹ¥
    0.12
    å®ļæľŁ
    0.10
    æ¯ıéĢ¢
    0.10
    æ¯ıå¹´
    0.10
    éĢĤæŶ
    0.10
    æ¯ıæľĪ
    0.10
    æ¯ı次
    0.09
     yearly
    0.09
    ä¸Ģå¹´ä¸Ģ度
    0.09
    Activations Density 0.095%

    No Known Activations