© 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. 61744
    Prev
    Next
    INDEX
    Explanations

    time durations in hours

    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
    ilor
    -0.08
    iev
    -0.08
    anna
    -0.08
    ima
    -0.07
    ier
    -0.07
    ugu
    -0.07
    ish
    -0.07
    bread
    -0.06
    bounding
    -0.06
     break
    -0.06
    POSITIVE LOGITS
    hek
    0.10
    idth
    0.10
    ظ
    0.10
    assen
    0.10
     Highlands
    0.10
     Lars
    0.10
    мÑı
    0.10
    heck
    0.09
    ÙĦا
    0.09
     pronto
    0.09
    Activations Density 0.035%

    No Known Activations