© 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. 4112
    Prev
    Next
    INDEX
    Explanations

    equestrian, horse, horses

    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
     Mist
    -0.08
    wiki
    -0.08
     mand
    -0.08
     siege
    -0.08
     Planning
    -0.08
    istro
    -0.08
     litter
    -0.08
     Alle
    -0.08
    esser
    -0.08
     asynchronously
    -0.07
    POSITIVE LOGITS
     horses
    0.15
     horse
    0.13
     mare
    0.13
     Horse
    0.12
     rider
    0.11
     hoof
    0.11
     herd
    0.11
    icorn
    0.11
    hoe
    0.11
    adero
    0.10
    Activations Density 0.357%

    No Known Activations