© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47899
    Prev
    Next
    INDEX
    Explanations

    combat sports decisions and officials

    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
     Incoming
    -0.10
     prism
    -0.10
    ych
    -0.09
    Skipping
    -0.09
     linear
    -0.09
    /left
    -0.08
     br
    -0.08
     chatt
    -0.08
     unloaded
    -0.08
    216
    -0.08
    POSITIVE LOGITS
     referee
    0.19
     referees
    0.17
     disqualified
    0.16
     controversial
    0.15
     rulings
    0.15
     offic
    0.15
     illegal
    0.15
     pin
    0.15
     judges
    0.14
     adjud
    0.14
    Activations Density 0.150%

    No Known Activations