© 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. 58634
    Prev
    Next
    INDEX
    Explanations

    support development and initiatives

    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
    /support
    -0.13
    support
    -0.11
     support
    -0.10
    -support
    -0.10
    Support
    -0.09
     Support
    -0.09
    bai
    -0.09
    ONG
    -0.09
     diluted
    -0.09
     supports
    -0.08
    POSITIVE LOGITS
    oli
    0.10
     endeavors
    0.08
    gate
    0.08
    inary
    0.08
     Barg
    0.08
    /as
    0.08
     Gur
    0.08
     verb
    0.08
    /on
    0.08
    Gate
    0.07
    Activations Density 0.031%

    No Known Activations