© 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. 49243
    Prev
    Next
    INDEX
    Explanations

    competitive sports

    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
     Dul
    -0.08
     filtered
    -0.07
    filled
    -0.07
    babel
    -0.07
     Retro
    -0.07
     filled
    -0.07
     cust
    -0.07
     filtering
    -0.07
     gent
    -0.07
    filtered
    -0.07
    POSITIVE LOGITS
     competit
    0.35
     competitive
    0.35
     Competitive
    0.28
     competitions
    0.27
    competitive
    0.26
     competed
    0.25
     compete
    0.25
     athletics
    0.25
     competition
    0.24
     athletes
    0.24
    Activations Density 0.543%

    No Known Activations