© 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. 8571
    Prev
    Next
    INDEX
    Explanations

    Soot, Grails, Adams, Hero, SCSS

    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
    /msg
    -0.09
     Fulton
    -0.09
    logan
    -0.09
    kee
    -0.08
     teng
    -0.08
    acus
    -0.08
    accent
    -0.08
     als
    -0.08
    edia
    -0.08
    izin
    -0.08
    POSITIVE LOGITS
    lessly
    0.09
    ky
    0.08
     bild
    0.08
    .Est
    0.07
    .Trim
    0.07
    hift
    0.07
     Bah
    0.07
    Brad
    0.07
    uto
    0.07
    alement
    0.07
    Activations Density 1.275%

    No Known Activations