© 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. 61712
    Prev
    Next
    INDEX
    Explanations

    java system packages

    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
    "testing
    -0.10
    ango
    -0.09
     rever
    -0.08
     smack
    -0.08
    oo
    -0.08
     Bare
    -0.08
    Reviews
    -0.07
     scr
    -0.07
    rows
    -0.07
     Ashton
    -0.07
    POSITIVE LOGITS
    iller
    0.10
    chor
    0.09
    acted
    0.09
    icals
    0.09
    é¢Ŀ
    0.08
    anta
    0.08
    .Collectors
    0.08
    ÑĤÑĮ
    0.08
    outu
    0.08
    bard
    0.08
    Activations Density 0.025%

    No Known Activations