© 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. 1631
    Prev
    Next
    INDEX
    Explanations

    quantities or amounts

    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
     attic
    -0.13
     an
    -0.12
     action
    -0.12
     umbrella
    -0.12
     interior
    -0.12
     a
    -0.11
     artwork
    -0.11
     animal
    -0.11
     album
    -0.10
     ace
    -0.10
    POSITIVE LOGITS
     few
    0.20
     lot
    0.17
    uteur
    0.17
    egis
    0.16
    ustin
    0.16
    uras
    0.16
     handful
    0.15
     variety
    0.15
     series
    0.15
    eron
    0.14
    Activations Density 2.071%

    No Known Activations