© 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. 8150
    Prev
    Next
    INDEX
    Explanations

    out of context quotes

    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
     mystery
    -0.08
     Cout
    -0.08
     conspiracy
    -0.08
     Mystery
    -0.08
    Und
    -0.08
    bottom
    -0.08
     spiked
    -0.08
     imp
    -0.07
     Compet
    -0.07
     inund
    -0.07
    POSITIVE LOGITS
     quotes
    0.15
     quotations
    0.14
     extracts
    0.14
     quote
    0.14
     quoting
    0.13
     cherry
    0.13
     extracted
    0.13
     excerpts
    0.12
     quoted
    0.12
     isolated
    0.12
    Activations Density 0.244%

    No Known Activations