© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2200
    Prev
    Next
    INDEX
    Explanations

    D.C

    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
    ouched
    -0.08
    included
    -0.08
     late
    -0.08
    ellan
    -0.08
     absorbing
    -0.08
    Constraint
    -0.07
    avel
    -0.07
    ugu
    -0.07
     Graf
    -0.07
    ocal
    -0.07
    POSITIVE LOGITS
     Hanson
    0.09
    peon
    0.09
    à¸ļ
    0.09
    apter
    0.09
    imetype
    0.09
    &R
    0.09
    .more
    0.09
    .KeyCode
    0.09
    à¯į
    0.08
    chten
    0.08
    Activations Density 0.082%

    No Known Activations