© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5421
    Prev
    Next
    INDEX
    Explanations

    professional sports teams

    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
     tripod
    -0.09
     drilled
    -0.09
     drill
    -0.09
     freshman
    -0.09
     halftime
    -0.09
     Rotary
    -0.09
     drills
    -0.09
     unpl
    -0.09
     annunci
    -0.09
     GK
    -0.09
    POSITIVE LOGITS
     franchises
    0.20
     franchise
    0.18
     league
    0.17
     teams
    0.17
     season
    0.13
     roster
    0.13
     League
    0.13
    -league
    0.13
     seasons
    0.13
     NFL
    0.12
    Activations Density 1.282%

    No Known Activations