© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55429
    Prev
    Next
    INDEX
    Explanations

    code keywords: `private`, `def`, `static`

    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
     Cour
    -0.09
    âĢ²
    -0.09
    unit
    -0.08
    cing
    -0.08
    clang
    -0.07
    Ack
    -0.07
     Runner
    -0.07
     kind
    -0.07
     Esp
    -0.07
    ingu
    -0.07
    POSITIVE LOGITS
    acha
    0.11
    odb
    0.10
     bord
    0.10
    ftware
    0.09
    .createTextNode
    0.09
     chu
    0.09
    ::-
    0.09
    iete
    0.09
    -range
    0.09
     Kathryn
    0.09
    Activations Density 0.038%

    No Known Activations