© 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. 91628
    Prev
    Next
    INDEX
    Explanations

    arena or stadium

    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
     bedside
    -0.09
     peg
    -0.09
     patrol
    -0.09
     cuck
    -0.09
    udit
    -0.09
     hike
    -0.08
    Trail
    -0.08
     hiking
    -0.08
    Alert
    -0.08
     modest
    -0.08
    POSITIVE LOGITS
     arena
    0.32
     arenas
    0.29
     Arena
    0.26
    Arena
    0.23
    arena
    0.23
     spectator
    0.22
     Gladiator
    0.21
     stadium
    0.21
     spectators
    0.20
     fighters
    0.18
    Activations Density 0.110%

    No Known Activations