© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2270
    Prev
    Next
    INDEX
    Explanations

    tabletop game systems

    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
     platform
    -0.10
     Platform
    -0.10
    /platform
    -0.10
    Desktop
    -0.10
     admitting
    -0.10
     platforms
    -0.10
    jis
    -0.10
     Fare
    -0.09
     defence
    -0.09
    ardi
    -0.09
    POSITIVE LOGITS
     tabletop
    0.14
     refl
    0.12
     dice
    0.11
     NPCs
    0.11
     PCs
    0.11
     Pathfinder
    0.10
     GM
    0.10
     rolls
    0.10
     NPC
    0.09
     flavorful
    0.09
    Activations Density 0.231%

    No Known Activations