© 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. 3449
    Prev
    Next
    INDEX
    Explanations

    fighting games

    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
    audi
    -0.10
     Rover
    -0.10
     Exped
    -0.10
     Cand
    -0.10
     Vive
    -0.09
    (dom
    -0.09
     dispenser
    -0.09
     Sprint
    -0.08
     Pam
    -0.08
     Dow
    -0.08
    POSITIVE LOGITS
     tournament
    0.23
     fighters
    0.22
     fighter
    0.20
     tournaments
    0.19
     Fighters
    0.18
     Capcom
    0.18
     Tournament
    0.18
     arcade
    0.17
     Fighter
    0.17
     Bison
    0.17
    Activations Density 0.260%

    No Known Activations