© 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. 57352
    Prev
    Next
    INDEX
    Explanations

    common law, filibuster, Court of Common Pleas

    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
    mate
    -0.10
    hus
    -0.10
     bay
    -0.09
    izarre
    -0.09
    olumn
    -0.08
    ragen
    -0.08
     Jacqu
    -0.08
     quer
    -0.08
    illery
    -0.08
     HY
    -0.08
    POSITIVE LOGITS
     tradition
    0.10
    elas
    0.09
     diluted
    0.08
    hind
    0.08
    developers
    0.08
    inds
    0.08
    lein
    0.08
     orphan
    0.08
     Tradition
    0.08
     elev
    0.08
    Activations Density 0.002%

    No Known Activations