© 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. 21333
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    éĢĢä¼ij
    -0.14
    èĢģ太太
    -0.13
    大人
    -0.13
    èĢģ人家
    -0.13
     retired
    -0.12
    èĢģçīĮ
    -0.12
    èĢģ头
    -0.12
    æįĭ
    -0.11
     пенÑģи
    -0.11
    èĢģ
    -0.11
    POSITIVE LOGITS
    æľªæĪIJå¹´
    0.13
    éĿĴå°ijå¹´
    0.11
    ç¨ļ
    0.11
    å°ijå¹´
    0.11
    å°ıä¼ĻåŃIJ
    0.11
    æĪIJéķ¿
    0.10
    çļĦæĪIJéķ¿
    0.10
    çİĭåŃIJ
    0.10
    大åѦçĶŁ
    0.10
    éķ¿å¤§
    0.09
    Activations Density 0.118%

    No Known Activations