© 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. 8198
    Prev
    Next
    INDEX
    Explanations

    stuck, to, or over

    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
    æľĢåIJİ
    -0.13
    åIJĮæĹ¶ä¹Ł
    -0.11
    æľĢç»Ī
    -0.11
    æľĢåIJİä¸Ģ次
    -0.10
    å°±è¿Ļæł·
    -0.10
    äºİæѤ
    -0.10
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.10
    å°ĸ
    -0.09
     Hats
    -0.09
    wahl
    -0.09
    POSITIVE LOGITS
    ä¸įåĨįæĺ¯
    0.11
    ä¸įåĨį
    0.11
    è¿Ľåħ¥äºĨ
    0.10
     pretty
    0.10
    åıĺå¾Ĺ
    0.10
    å¼Ģå§ĭäºĨ
    0.09
    没äºĨ
    0.09
     becomes
    0.09
    ãģĮå§ĭ
    0.09
     proceedings
    0.09
    Activations Density 0.082%

    No Known Activations