© 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. 4560
    Prev
    Next
    INDEX
    Explanations

    countries and governments

    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
    odb
    -0.07
     sources
    -0.07
     Emerald
    -0.06
    ubo
    -0.06
     disproportionate
    -0.06
     popular
    -0.06
    wyn
    -0.06
    une
    -0.06
     bid
    -0.06
     Tears
    -0.06
    POSITIVE LOGITS
     Governments
    0.11
    uell
    0.11
     governments
    0.11
     economies
    0.11
     carousel
    0.11
     Instit
    0.10
     Inst
    0.10
    organisation
    0.10
    Govern
    0.10
    inema
    0.10
    Activations Density 0.297%

    No Known Activations