© 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. 16757
    Prev
    Next
    INDEX
    Explanations

    sanctions

    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¥ł
    -0.09
    é¸Ń
    -0.09
    çļĩ宫
    -0.08
    erval
    -0.08
    æī¾åĽŀ
    -0.08
    drv
    -0.08
    duck
    -0.08
    _FM
    -0.08
    å¯Ŀ
    -0.08
    æŀĦæĪIJäºĨ
    -0.08
    POSITIVE LOGITS
    åĪ¶è£ģ
    0.11
    ç»ķ
    0.10
     sanctions
    0.10
    ç½ļ
    0.10
    ç½ļ款
    0.10
    åĶı
    0.10
    FINE
    0.09
    æ¶īå«Į
    0.09
    éľī
    0.09
    åѤ
    0.09
    Activations Density 0.069%

    No Known Activations