© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 1300
    Prev
    Next
    INDEX
    Explanations

    harbor, insider, reductase, resorption

    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
    chants
    -0.11
     conveniently
    -0.08
    cene
    -0.08
    lest
    -0.08
    imed
    -0.08
    kte
    -0.08
    ppo
    -0.08
    ARI
    -0.08
     Filed
    -0.08
    ereg
    -0.08
    POSITIVE LOGITS
    æ¡Ī
    0.09
    ell
    0.09
    shire
    0.09
     getLogger
    0.09
     DISTINCT
    0.08
     Violet
    0.08
    Saga
    0.08
     nack
    0.08
     grou
    0.08
     Slee
    0.08
    Activations Density 0.210%

    No Known Activations