© 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. 37196
    Prev
    Next
    INDEX
    Explanations

    Chinese and Japanese characters

    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
    æ´ŀ
    -0.09
    èĦ¯
    -0.08
     unre
    -0.08
    æĺ¯æľĢ好çļĦ
    -0.08
    æĺ±
    -0.08
    bose
    -0.08
    гÑĢан
    -0.08
    ocha
    -0.08
    olle
    -0.08
     Jeżeli
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĪĻ
    0.10
    ä¸İæѤ
    0.10
    ä¼¼ä¹İæĺ¯
    0.09
    åIJĮæł·æĺ¯
    0.09
    éļ¾éģĵ
    0.09
    åĹĴ
    0.08
    è¯Ńæĸĩ
    0.08
    缮çļĦåľ¨äºİ
    0.08
    _tgt
    0.08
     gì
    0.08
    Activations Density 0.073%

    No Known Activations