© 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. 61691
    Prev
    Next
    INDEX
    Explanations

    collapse structures, prices, airways

    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
    er
    -0.10
    est
    -0.09
    -up
    -0.09
    fore
    -0.09
    ard
    -0.08
    iol
    -0.08
    aller
    -0.08
    achi
    -0.08
    -ste
    -0.08
    arger
    -0.08
    POSITIVE LOGITS
    ible
    0.11
    usher
    0.11
    ibility
    0.11
    IBLE
    0.10
    Ñĭваем
    0.10
    ibly
    0.10
    ibilities
    0.10
    ibles
    0.10
    ibilit
    0.09
    .generated
    0.09
    Activations Density 0.006%

    No Known Activations