© 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. 59460
    Prev
    Next
    INDEX
    Explanations

    Thanksgiving, Chrysler, Greenland

    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
    ickle
    -0.09
    尾巴
    -0.09
    igt
    -0.08
    ä»Ļå¢ĥ
    -0.08
    çĪ¹
    -0.08
    åĵ¥
    -0.08
    çļĦå°±æĺ¯
    -0.08
     Nah
    -0.08
    亵
    -0.08
    åŀĭä¼ģä¸ļ
    -0.08
    POSITIVE LOGITS
    à¸ĩ
    0.10
    ãģĦãĤĭ
    0.10
    odu
    0.10
    ãģĦãĤĭãģ¨
    0.10
    er
    0.09
     Dinner
    0.08
    /OR
    0.08
    æ®Ħ
    0.08
    ãģĦãģ¾ãģĻ
    0.08
    isma
    0.08
    Activations Density 0.004%

    No Known Activations