© 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. 8625
    Prev
    Next
    INDEX
    Explanations

    over years and time

    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
    iol
    -0.08
     started
    -0.08
     AFTER
    -0.08
     Quando
    -0.08
    fore
    -0.08
     Magnet
    -0.08
     begun
    -0.08
     report
    -0.08
    usher
    -0.08
    -start
    -0.08
    POSITIVE LOGITS
     accumulating
    0.12
     intermitt
    0.12
     continually
    0.11
     intermittent
    0.11
    SOR
    0.10
     continuously
    0.10
     constantly
    0.10
     repeatedly
    0.10
     meanwhile
    0.10
     accumulate
    0.10
    Activations Density 0.274%

    No Known Activations