© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 753
    Prev
    Next
    INDEX
    Explanations

    game points, buy, build, races

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -document
    -0.10
     mojo
    -0.10
    coll
    -0.09
     mgr
    -0.09
    :no
    -0.09
     champ
    -0.09
     International
    -0.09
     collage
    -0.09
     calend
    -0.09
    orado
    -0.09
    POSITIVE LOGITS
     gameplay
    0.13
     player
    0.12
     bonus
    0.12
     enemies
    0.11
     bonuses
    0.11
     mechanic
    0.11
     boosts
    0.11
     abilities
    0.11
     multiplayer
    0.11
     rewards
    0.10
    Activations Density 0.823%

    No Known Activations