© 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. 8732
    Prev
    Next
    INDEX
    Explanations

    determiners and quantity markers

    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
    .proto
    -0.09
    ught
    -0.09
    è¿Ļ段
    -0.08
    å·²æĺ¯
    -0.07
     Friedrich
    -0.07
    éĽī
    -0.07
    .toArray
    -0.07
    ugi
    -0.07
    reator
    -0.07
    èĻ¹æ¡¥
    -0.07
    POSITIVE LOGITS
     ones
    0.21
     Ones
    0.14
     celle
    0.12
     thereof
    0.11
    ones
    0.10
     celui
    0.10
    æıĨ
    0.09
    ãģĿãĤĮãģ¯
    0.09
    两个人
    0.09
    åįİ缼
    0.09
    Activations Density 0.627%

    No Known Activations