© 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. 58922
    Prev
    Next
    INDEX
    Explanations

    code blocks ending in parentheses

    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
     temporarily
    -0.14
     temporary
    -0.13
     Temporary
    -0.11
    temporary
    -0.10
     cade
    -0.09
    endor
    -0.09
    eph
    -0.09
     transient
    -0.09
    .await
    -0.08
     instrumentation
    -0.08
    POSITIVE LOGITS
     refin
    0.10
    ev
    0.10
     Hose
    0.10
    oo
    0.09
     yell
    0.09
    /files
    0.08
    emple
    0.08
    (By
    0.08
     gaps
    0.08
    pu
    0.08
    Activations Density 0.011%

    No Known Activations