© 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. 4790
    Prev
    Next
    INDEX
    Explanations

    SELECT *

    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
    äºİ
    -0.07
    DAL
    -0.06
     Notebook
    -0.06
     Sheldon
    -0.06
    eldon
    -0.06
     nostr
    -0.06
     Gin
    -0.06
    Andrew
    -0.06
    /trunk
    -0.06
    oose
    -0.06
    POSITIVE LOGITS
     DISTINCT
    0.13
    ByExample
    0.11
     distinct
    0.11
    slaught
    0.11
    usu
    0.11
    UFF
    0.11
    brands
    0.11
    ripp
    0.10
     Thompson
    0.10
     conclus
    0.10
    Activations Density 0.139%

    No Known Activations