© 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. 61178
    Prev
    Next
    INDEX
    Explanations

    change and modify

    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
    ha
    -0.10
     process
    -0.09
     suddenly
    -0.09
    CKET
    -0.08
     Press
    -0.08
     downgrade
    -0.08
     nearing
    -0.08
    pler
    -0.08
    gers
    -0.08
    anst
    -0.08
    POSITIVE LOGITS
    wort
    0.10
    eus
    0.09
    lua
    0.08
    berger
    0.08
    yms
    0.08
     tempered
    0.08
    ót
    0.08
     hopefully
    0.08
     tractor
    0.08
    inerary
    0.08
    Activations Density 0.094%

    No Known Activations