© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24062
    Prev
    Next
    INDEX
    Explanations

    Japan and Japanese culture

    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
    Negative Logits
    级以ä¸Ĭ
    -0.09
    è°Ŀ
    -0.09
    ãģĻãģ§
    -0.09
    æĸ°çĸĨ
    -0.09
    çī¦
    -0.08
    è¦ģä¹Ī
    -0.08
    é¦į
    -0.08
    ãĤ·ãĥ§ãĥ¼
    -0.08
    çĵ
    -0.08
    çī²
    -0.08
    POSITIVE LOGITS
    åľ¨æĹ¥æľ¬
    0.21
    æĹ¥æľ¬
    0.19
     Japan
    0.16
    Japan
    0.15
     Japanese
    0.15
    Japanese
    0.14
     japan
    0.14
    æĹ¥æľ¬äºº
    0.13
     Tokyo
    0.13
     Osaka
    0.13
    Activations Density 3.681%

    No Known Activations