© 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. 55035
    Prev
    Next
    INDEX
    Explanations

    Very Frank, F-grade Mizuno, : Python, Love Is

    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
    errat
    -0.10
    otel
    -0.10
    ater
    -0.08
     boa
    -0.08
    hy
    -0.08
    _ENV
    -0.08
    amon
    -0.08
     Maj
    -0.08
     Minor
    -0.08
     maxim
    -0.08
    POSITIVE LOGITS
    egen
    0.09
    oz
    0.09
    fid
    0.09
    Regional
    0.09
     Dere
    0.09
    peng
    0.08
    ect
    0.08
    asco
    0.08
     Coch
    0.08
    agit
    0.08
    Activations Density 0.003%

    No Known Activations