© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 34234
    Prev
    Next
    INDEX
    Explanations

    winner or loser of a contest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     Successfully
    -0.10
     success
    -0.10
     successfully
    -0.10
     succeed
    -0.10
    Ñĥн
    -0.10
     assault
    -0.10
    athe
    -0.10
    meldung
    -0.10
    URED
    -0.09
    .sy
    -0.09
    POSITIVE LOGITS
     congrat
    0.20
     rematch
    0.20
     losers
    0.20
     loser
    0.19
     congratulate
    0.19
     congratulations
    0.18
     consolation
    0.18
     celebrations
    0.16
     Congratulations
    0.16
     vict
    0.16
    Activations Density 0.621%

    No Known Activations