© 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. 8164
    Prev
    Next
    INDEX
    Explanations

    exposure to

    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
     reserves
    -0.10
    jam
    -0.10
     Tin
    -0.09
     Vig
    -0.09
    oned
    -0.09
    lod
    -0.09
    owards
    -0.09
    olas
    -0.08
     Price
    -0.08
    plorer
    -0.08
    POSITIVE LOGITS
     exposure
    0.10
     glue
    0.09
     Exposure
    0.09
     expose
    0.09
     risks
    0.09
    zee
    0.08
    felt
    0.08
    166
    0.08
    ncia
    0.08
     exposing
    0.08
    Activations Density 0.062%

    No Known Activations