© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1772
    Prev
    Next
    INDEX
    Explanations

    car, driving, vehicles, automobiles

    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
     Lod
    -0.09
    elson
    -0.09
     Kro
    -0.09
    kos
    -0.09
     Ven
    -0.08
    lain
    -0.08
     proces
    -0.08
    .dart
    -0.08
    tee
    -0.08
     Toshiba
    -0.08
    POSITIVE LOGITS
     parked
    0.16
     vehicle
    0.14
     vehicles
    0.13
    riages
    0.13
     cars
    0.12
     car
    0.11
    /tr
    0.11
    .drive
    0.11
    (vehicle
    0.11
    ibbean
    0.11
    Activations Density 1.576%

    No Known Activations