© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21166
    Prev
    Next
    INDEX
    Explanations

    disabilities and illness

    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
    éħ©
    -0.09
    åıijçĶŁäºĨ
    -0.09
    è¿Ļ对äºİ
    -0.09
    大家éĥ½åľ¨
    -0.09
    å°±æĺ¯ä¸Ģ个
    -0.09
    asion
    -0.09
    å¤ĸç±į
    -0.09
    æ¼ķ
    -0.09
    oad
    -0.09
    åİŁæĿ¥æĺ¯
    -0.09
    POSITIVE LOGITS
    ä¸ĵç͍
    0.11
    åIJĮèĥŀ
    0.09
    ullah
    0.09
    Immediate
    0.08
    å®¶å±ŀ
    0.08
    è·Łè¸ª
    0.08
    -friendly
    0.08
    ened
    0.08
    à¹Ģà¸ĭล
    0.08
     whose
    0.08
    Activations Density 0.249%

    No Known Activations