© 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. 116693
    Prev
    Next
    INDEX
    Explanations

    scoring goals and touchdowns

    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
    azen
    -0.14
     flop
    -0.11
     Mang
    -0.11
    idas
    -0.11
    *)_
    -0.11
    Ctl
    -0.10
     fier
    -0.10
     USAGE
    -0.10
    ongo
    -0.10
     ARTICLE
    -0.10
    POSITIVE LOGITS
     scored
    0.22
     touchdown
    0.20
     touchdowns
    0.19
     scoring
    0.18
     points
    0.14
     score
    0.13
     victory
    0.13
     goals
    0.13
     scores
    0.13
     victories
    0.12
    Activations Density 0.324%

    No Known Activations