© 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. 59231
    Prev
    Next
    INDEX
    Explanations

    United States courts and trade

    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
    è¸ıå®ŀ
    -0.10
    çī¹æĸ¯
    -0.09
    ilion
    -0.09
    utton
    -0.09
    -panel
    -0.08
    èĶº
    -0.08
    èIJ½åľ¨
    -0.08
    åĵĴ
    -0.08
    èIJ½
    -0.08
    ubby
    -0.08
    POSITIVE LOGITS
    äºĭçī©
    0.09
    饱
    0.08
    ä¼ļåijĺ
    0.08
    ç¾İ好çĶŁæ´»
    0.08
    cuts
    0.08
     afr
    0.07
    ä¿¡æģ¯
    0.07
    çī¹èī²çļĦ
    0.07
    书æ³ķ
    0.07
    æ°Ķæģ¯
    0.07
    Activations Density 0.202%

    No Known Activations