© 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. 3184
    Prev
    Next
    INDEX
    Explanations

    parameterization

    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
    brush
    -0.08
    ey
    -0.08
    ampo
    -0.08
     Fraser
    -0.08
    eil
    -0.08
    elly
    -0.07
     absent
    -0.07
    elman
    -0.07
    elson
    -0.07
    è½½
    -0.07
    POSITIVE LOGITS
    etric
    0.14
    .AddWithValue
    0.11
    etros
    0.11
    ters
    0.11
    ization
    0.10
    isation
    0.10
    izations
    0.10
    ArrayOf
    0.10
    izable
    0.10
    ater
    0.09
    Activations Density 0.056%

    No Known Activations