© 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. 2357
    Prev
    Next
    INDEX
    Explanations

    § legal code citations

    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
    ноп
    -0.10
    aiser
    -0.10
     Gross
    -0.09
    ewood
    -0.09
    Trader
    -0.09
    ymes
    -0.09
    unter
    -0.09
     Bauer
    -0.09
    andler
    -0.09
     Epstein
    -0.09
    POSITIVE LOGITS
    amp
    0.10
    ube
    0.09
     Brah
    0.07
    leted
    0.07
     fals
    0.07
     accompanying
    0.07
     dod
    0.07
     Carnival
    0.07
    amer
    0.07
    <![
    0.07
    Activations Density 0.003%

    No Known Activations