© 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. 7835
    Prev
    Next
    INDEX
    Explanations

    is usually

    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
    è¿Ļæł·çļĦè¯Ŀ
    -0.10
    大家
    -0.10
    大家éĥ½åľ¨
    -0.09
    éĿłçĿĢ
    -0.09
    ä½łèĥ½
    -0.09
    大家åı¯ä»¥
    -0.09
    æ§Į
    -0.09
    ä»ħ代表
    -0.08
    lee
    -0.08
    bridge
    -0.08
    POSITIVE LOGITS
     themselves
    0.10
    å°Ĩåħ¶
    0.10
    称ä¹ĭ
    0.10
    ä¹ŁçŁ¥éģĵ
    0.09
    ousel
    0.09
    ccoli
    0.08
    æĬĬå®ĥ
    0.08
    称ä¹ĭ为
    0.08
    æľīæľºä¼ļ
    0.08
    åIJĮæĹ¶ä¹Łæĺ¯
    0.08
    Activations Density 0.173%

    No Known Activations