© 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. 91140
    Prev
    Next
    INDEX
    Explanations

    video games and gaming

    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
     Valentine
    -0.09
    alian
    -0.09
     teal
    -0.09
     Darling
    -0.09
     tumble
    -0.08
     ambassadors
    -0.08
     Windsor
    -0.08
     linen
    -0.08
     togg
    -0.08
     Tooltip
    -0.08
    POSITIVE LOGITS
     videog
    0.42
     gaming
    0.41
     games
    0.36
     Gaming
    0.34
     Nintendo
    0.31
     gamer
    0.31
     game
    0.31
     Playstation
    0.31
     Xbox
    0.30
     gamers
    0.30
    Activations Density 0.177%

    No Known Activations