© 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. 60872
    Prev
    Next
    INDEX
    Explanations

    lipid and tariff terms

    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
    å¿ħä¸įåı¯
    -0.10
    æīĵå¾Ĺ
    -0.10
    åĪĽæĸ°é©±åĬ¨
    -0.09
    å¾ĹäºĨ
    -0.09
    ers
    -0.09
    аÑħ
    -0.09
    èĪ
    -0.09
    prit
    -0.09
    izer
    -0.09
    æĦıå¢ĥ
    -0.09
    POSITIVE LOGITS
    icie
    0.09
    汪
    0.09
    æľīæĿ¡ä»¶
    0.09
    æ¾İ
    0.08
    unker
    0.08
    ly
    0.08
    bart
    0.08
    theless
    0.08
    /octet
    0.08
    éĹ°
    0.08
    Activations Density 0.004%

    No Known Activations