© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54885
    Prev
    Next
    INDEX
    Explanations

    China and Chinese entities

    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
    éķķ
    -0.10
    ä½ľåĵģåĨħ容
    -0.09
    èģĶéĤ¦
    -0.09
    åĨħ马
    -0.09
    å¾·å·ŀ
    -0.09
    æĸ¼æĺ¯
    -0.09
    åİ©
    -0.09
    è¶ĬæĿ¥è¶Ĭ大
    -0.09
    åİĨåı²æĸ°
    -0.08
    åĨħéĺģ
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸ŃåĽ½
    0.14
     China
    0.12
     Chinese
    0.12
     Beijing
    0.12
     Shanghai
    0.11
    China
    0.11
    æĪIJ为ä¸ŃåĽ½
    0.11
    inyin
    0.11
     Qin
    0.10
     Shan
    0.10
    Activations Density 1.378%

    No Known Activations