© 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. 48046
    Prev
    Next
    INDEX
    Explanations

    game genres and types

    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
     nickname
    -0.10
    è±
    -0.09
    icher
    -0.09
     Preferred
    -0.09
    stral
    -0.08
     Starter
    -0.08
     Auxiliary
    -0.08
     Actors
    -0.08
    Broadcast
    -0.08
    Writes
    -0.08
    POSITIVE LOGITS
     interactive
    0.20
     simulation
    0.18
     puzzle
    0.18
     game
    0.17
     puzzles
    0.17
     arcade
    0.16
     Interactive
    0.16
    interactive
    0.16
     guessing
    0.16
     games
    0.16
    Activations Density 0.329%

    No Known Activations