© 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. 18440
    Prev
    Next
    INDEX
    Explanations

    boxing matches and boxers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     skateboard
    -0.10
     Agency
    -0.09
    stoff
    -0.09
     Scre
    -0.09
     Sark
    -0.09
     Lori
    -0.09
     horny
    -0.09
     Brake
    -0.09
    ovie
    -0.09
     Lair
    -0.09
    POSITIVE LOGITS
     boxing
    0.48
     Boxing
    0.42
     boxer
    0.39
     punches
    0.35
    boxing
    0.32
     punch
    0.32
     punching
    0.31
     fighters
    0.28
     Punch
    0.28
     fighter
    0.27
    Activations Density 0.359%

    No Known Activations