© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20493
    Prev
    Next
    INDEX
    Explanations

    continents and countries

    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
    é¼ĵ
    -0.09
     Axe
    -0.09
     çiz
    -0.09
    å¯ĨéĽĨ
    -0.08
    дал
    -0.08
     Romance
    -0.08
    çĭŃ
    -0.08
    æĹıèĩªæ²»
    -0.08
    éĥ¨ä»¶
    -0.08
    èĢĺ
    -0.08
    POSITIVE LOGITS
    é¦ĸå®¶
    0.10
    åħ¶ä»ĸåĽ½å®¶
    0.10
    ä¹ĥèĩ³
    0.10
    åħ±åIJĮ
    0.09
    æľĢ大çļĦ
    0.09
    æĺİçıł
    0.09
    å͝ä¸Ģ
    0.09
    å¤ļä¸ªåĽ½å®¶
    0.09
    æľĢ好çļĦ
    0.09
     sideways
    0.09
    Activations Density 0.100%

    No Known Activations