© 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. 612
    Prev
    Next
    INDEX
    Explanations

    sanctions and restrictions

    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
    æ³ķå¾ĭ顾éĹ®
    -0.10
    ä¸İæŶ
    -0.10
    æ¿Ł
    -0.09
    PFN
    -0.09
    ä¸ĢçĶŁ
    -0.09
    æĿ¥ä¸įåıĬ
    -0.09
    æµİ
    -0.09
    _dt
    -0.09
     Inst
    -0.09
     Charity
    -0.09
    POSITIVE LOGITS
     boycott
    0.15
    åģľçĶµ
    0.11
    延éķ¿
    0.11
    æĬµåĪ¶
    0.11
     embargo
    0.10
     restrictions
    0.10
    å°ģéĶģ
    0.10
    åłµ
    0.10
    åģľäº§
    0.10
    éĸī
    0.09
    Activations Density 0.091%

    No Known Activations