© 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. 4751
    Prev
    Next
    INDEX
    Explanations

    secondary, primary, aspects

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ird
    -0.10
    iven
    -0.09
     freopen
    -0.09
     cadre
    -0.08
    [res
    -0.08
    /rec
    -0.08
     odom
    -0.08
    pron
    -0.08
     Mast
    -0.08
     compr
    -0.08
    POSITIVE LOGITS
     another
    0.09
    (second
    0.09
     tertiary
    0.09
    another
    0.09
     softer
    0.09
    âĢ¦but
    0.08
    SECOND
    0.08
    âĢ¦the
    0.08
    adem
    0.08
     Dixon
    0.08
    Activations Density 1.190%

    No Known Activations