© 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. 8077
    Prev
    Next
    INDEX
    Explanations

    defeating opponents

    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
     Ingen
    -0.11
    enet
    -0.10
     recl
    -0.10
     refresh
    -0.10
     Articles
    -0.10
     Parts
    -0.09
    enos
    -0.09
     Masc
    -0.09
     misled
    -0.09
    olt
    -0.09
    POSITIVE LOGITS
     defeating
    0.17
     defeat
    0.17
     defeated
    0.16
     defeats
    0.15
     opponent
    0.14
     underestimate
    0.13
     evenly
    0.13
     formidable
    0.12
     effortless
    0.12
     frontal
    0.11
    Activations Density 0.071%

    No Known Activations