© 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. 1582
    Prev
    Next
    INDEX
    Explanations

    developmental, economic, and environmental terms

    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
    idan
    -0.09
     lxml
    -0.09
    inka
    -0.09
     pyt
    -0.09
     fakt
    -0.09
     Luxury
    -0.08
     Restaurants
    -0.08
    icorn
    -0.08
    <!--↵
    -0.08
    bak
    -0.08
    POSITIVE LOGITS
     &
    0.10
    .Ed
    0.09
    ...,
    0.08
     Center
    0.08
    ology
    0.08
     division
    0.08
     centre
    0.08
     ^(
    0.08
     center
    0.08
    PLUS
    0.08
    Activations Density 2.965%

    No Known Activations