© 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. 5000
    Prev
    Next
    INDEX
    Explanations

    rock cut, band, pool, outcropping

    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
    Negative Logits
    {/*
    -0.11
     Goose
    -0.10
     Financing
    -0.09
    ched
    -0.09
     Tent
    -0.09
     doub
    -0.08
    ToUpdate
    -0.08
     Feather
    -0.08
    cad
    -0.08
    chrift
    -0.08
    POSITIVE LOGITS
     Quarry
    0.10
    abil
    0.10
     quarry
    0.10
     quar
    0.09
    ledge
    0.09
    steady
    0.09
     formations
    0.09
     nacional
    0.09
    -solid
    0.09
    ds
    0.08
    Activations Density 0.176%

    No Known Activations