© 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. 63751
    Prev
    Next
    INDEX
    Explanations

    compete / competition / competing

    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
    äºĪ以
    -0.09
    顺
    -0.09
    пад
    -0.08
    edException
    -0.08
    own
    -0.08
    oz
    -0.08
    wake
    -0.08
    åIJĪèµĦ
    -0.08
    -inv
    -0.08
    åĬłä»¥
    -0.08
    POSITIVE LOGITS
    ä¸Ĭå²Ĺ
    0.13
    ç«ŀ
    0.12
    æĬ¢
    0.11
    奪
    0.11
    夺
    0.10
    æ¿ĢçĥĪçļĦ
    0.10
    APE
    0.10
     Competition
    0.10
    競
    0.10
     Liber
    0.10
    Activations Density 0.038%

    No Known Activations