© 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. 3252
    Prev
    Next
    INDEX
    Explanations

    storm forecasts and movements

    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
     Summers
    -0.10
     Dawn
    -0.08
     rep
    -0.08
    anzi
    -0.08
     Hawth
    -0.08
     permanently
    -0.08
    _known
    -0.08
     gloss
    -0.08
     permanent
    -0.08
    oric
    -0.08
    POSITIVE LOGITS
     forecast
    0.12
     advis
    0.12
     Dop
    0.12
     Forecast
    0.11
    enate
    0.11
     southeastern
    0.11
     statewide
    0.10
     powerful
    0.10
    forecast
    0.10
     widespread
    0.10
    Activations Density 0.155%

    No Known Activations