© 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. 1928
    Prev
    Next
    INDEX
    Explanations

    countries and regions worldwide

    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
     Syrians
    -0.11
     Iranians
    -0.11
     Saudis
    -0.11
     Indones
    -0.11
    imin
    -0.11
     Rw
    -0.10
     Mosul
    -0.10
     IDR
    -0.10
     Malays
    -0.10
    alars
    -0.10
    POSITIVE LOGITS
     countries
    0.22
     regions
    0.21
     worldwide
    0.18
     Countries
    0.17
    countries
    0.15
     continents
    0.15
     jurisdictions
    0.15
     region
    0.14
     Regions
    0.14
     continental
    0.13
    Activations Density 2.423%

    No Known Activations