© 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. 61439
    Prev
    Next
    INDEX
    Explanations

    mathematical problems and specific contexts

    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
     nouvel
    -0.15
    ãĤ¢
    -0.12
    à¸Ń
    -0.12
     Andy
    -0.12
     degli
    -0.12
     ãĤ¢
    -0.12
     an
    -0.12
     dell
    -0.12
    —an
    -0.12
     ÐIJ
    -0.11
    POSITIVE LOGITS
     Trot
    0.08
    veau
    0.07
     LoggerFactory
    0.07
    STM
    0.07
    .Ticks
    0.07
    ¶ļ
    0.07
    (SK
    0.06
    odzi
    0.06
    attr
    0.06
    _GPS
    0.06
    Activations Density 0.817%

    No Known Activations