© 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. 31448
    Prev
    Next
    INDEX
    Explanations

    game simulator and battlefield

    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
     imageURL
    -0.11
     Setter
    -0.11
     flakes
    -0.10
     Svg
    -0.10
     migraine
    -0.10
    olini
    -0.10
     televis
    -0.09
    (site
    -0.09
    noop
    -0.09
     photographic
    -0.09
    POSITIVE LOGITS
     gameplay
    0.38
     multiplayer
    0.34
     game
    0.32
     Gameplay
    0.31
     player
    0.30
    -game
    0.29
     players
    0.28
     DLC
    0.27
     playable
    0.26
     NPCs
    0.26
    Activations Density 0.917%

    No Known Activations