© 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. 430
    Prev
    Next
    INDEX
    Explanations

    United Kingdom and English speaking 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
     Weiner
    -0.12
     Baum
    -0.11
     Sag
    -0.11
     Macy
    -0.11
     Congressman
    -0.10
     Nebraska
    -0.10
     Caj
    -0.10
    dba
    -0.10
     Wisconsin
    -0.10
     Congressional
    -0.10
    POSITIVE LOGITS
     plc
    0.17
     British
    0.17
     England
    0.17
     Britain
    0.17
    Britain
    0.16
     UK
    0.16
    British
    0.15
     Brexit
    0.15
     Nigel
    0.15
    England
    0.15
    Activations Density 2.703%

    No Known Activations