© 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. 3259
    Prev
    Next
    INDEX
    Explanations

    countries

    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
     USA
    -0.11
    vern
    -0.08
     Netherlands
    -0.08
    usic
    -0.08
     United
    -0.08
    USA
    -0.08
    ertil
    -0.08
    ersistent
    -0.08
     sic
    -0.08
    erta
    -0.08
    POSITIVE LOGITS
    beck
    0.09
    ims
    0.08
     Bs
    0.08
     Bever
    0.08
    iore
    0.08
    kes
    0.08
     sons
    0.08
     nicknamed
    0.08
    athers
    0.08
     advoc
    0.07
    Activations Density 0.044%

    No Known Activations