© 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. 4579
    Prev
    Next
    INDEX
    Explanations

    ancient and evolutionary history

    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
     growing
    -0.09
    .SK
    -0.09
     ley
    -0.09
    TEX
    -0.09
     variant
    -0.09
    .study
    -0.09
     sik
    -0.09
    untime
    -0.09
     Growing
    -0.09
    variant
    -0.08
    POSITIVE LOGITS
     evolutionary
    0.13
     ancestral
    0.12
     ancestors
    0.11
     ance
    0.11
     shared
    0.10
     primitive
    0.10
     Evolution
    0.09
     Evo
    0.09
     Camb
    0.09
     fossil
    0.09
    Activations Density 0.311%

    No Known Activations