© 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. 1737
    Prev
    Next
    INDEX
    Explanations

    events that have started or finished

    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
     ensuing
    -0.09
    foundland
    -0.08
     hoje
    -0.08
     eventually
    -0.08
     thereafter
    -0.08
     subsequently
    -0.08
    later
    -0.08
     eventual
    -0.07
     interes
    -0.07
     additionally
    -0.07
    POSITIVE LOGITS
     previous
    0.47
     previously
    0.41
     earlier
    0.38
     Previous
    0.36
    previous
    0.35
    Previous
    0.30
     Previously
    0.29
     prior
    0.28
     Earlier
    0.28
    Previously
    0.26
    Activations Density 3.231%

    No Known Activations