© 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. 733
    Prev
    Next
    INDEX
    Explanations

    tariff, tariffs, taxation

    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
    æ·Į
    -0.10
    æľĢåħ³éĶ®
    -0.10
    缣
    -0.10
    侥幸
    -0.10
    èIJ¼
    -0.09
    å¿Ĵ
    -0.09
    äºī夺
    -0.09
    èļĢ
    -0.09
    æľĢåħ³éĶ®çļĦ
    -0.09
    çĽijæĬ¤
    -0.09
    POSITIVE LOGITS
    å¾ģæĶ¶
    0.16
    æѧè§Ĩ
    0.11
     tariffs
    0.11
     taxes
    0.11
    å¾ģ
    0.11
    åħ³ç¨İ
    0.10
    ç¨İ
    0.10
    ç½ļ款
    0.10
     taxation
    0.10
    æĶ¶è´¹
    0.10
    Activations Density 0.071%

    No Known Activations