© 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. 8570
    Prev
    Next
    INDEX
    Explanations

    integer data types

    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
     Fi
    -0.10
    allo
    -0.10
    .parseDouble
    -0.10
    acer
    -0.09
    rary
    -0.09
    /org
    -0.09
    rix
    -0.09
    ary
    -0.09
    ascus
    -0.09
    pez
    -0.09
    POSITIVE LOGITS
    0.12
    .parseInt
    0.09
    imon
    0.09
    ima
    0.09
    istics
    0.08
    iman
    0.08
    ãĥ¡ãĥ³ãĥĪ
    0.08
    ampo
    0.07
    ubber
    0.07
    ems
    0.07
    Activations Density 0.093%

    No Known Activations