© 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. 6096
    Prev
    Next
    INDEX
    Explanations

    County, town, or place names

    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
    å°±è¿ŀ
    -0.09
    thin
    -0.09
    è¿ĻæĿ¡
    -0.09
    æ¼
    -0.09
    è¿Ļä¹Ī说
    -0.08
    ä¸Ģå±Ĥ
    -0.08
    emic
    -0.08
    eya
    -0.08
    æĪ´ä¸Ĭ
    -0.08
    桨
    -0.08
    POSITIVE LOGITS
    磾
    0.09
     Kami
    0.09
    çŁŃæľŁåĨħ
    0.09
    马桶
    0.09
    íĦ±
    0.09
    åŁİéĩĮ
    0.09
    æ´¥
    0.08
    åİķ
    0.08
    京津
    0.08
    cook
    0.08
    Activations Density 0.130%

    No Known Activations