© 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. 51884
    Prev
    Next
    INDEX
    Explanations

    standardized tests and performance measures

    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
    iline
    -0.10
     tiên
    -0.09
     Blast
    -0.08
    EXT
    -0.08
    è¡ĮåĬ¨
    -0.08
    é¾Ļ头
    -0.08
    ç»ıèIJ¥æ¨¡å¼ı
    -0.08
    è´¨
    -0.08
    æĬ½åĩº
    -0.08
    LOGGER
    -0.08
    POSITIVE LOGITS
    鸲
    0.11
    å¿¿
    0.10
    缸åħ³åĨħ容
    0.10
    ãĥĨãĤ¹ãĥĪ
    0.10
     Gri
    0.10
    çijŀ士
    0.10
     tests
    0.10
    è¿Ļ个èģĮä¸ļ
    0.09
     Battery
    0.09
    _cookies
    0.09
    Activations Density 0.127%

    No Known Activations