© 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. 37163
    Prev
    Next
    INDEX
    Explanations

    now or today

    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
    æľīè¿ĩ
    -0.09
    æĸ°åĮº
    -0.09
    éĻ¢åī¯éĻ¢éķ¿
    -0.08
    çĵ·åĻ¨
    -0.08
    å½¢åĬ¿
    -0.08
    çĦ¶åIJİåĨį
    -0.08
    éĹ²
    -0.08
    æ£ł
    -0.08
    å¢Ł
    -0.08
    à¸Ļาà¸Ļ
    -0.08
    POSITIVE LOGITS
     now
    0.12
    ä»ĬæĹ¥
    0.12
    çİ°åľ¨
    0.11
     today
    0.11
     ÑģейÑĩаÑģ
    0.11
     اÙĦØ¢ÙĨ
    0.11
    ä»Ĭ天
    0.11
    稳
    0.10
    马ä¸Ĭ
    0.10
     soon
    0.10
    Activations Density 0.094%

    No Known Activations