© 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. 3352
    Prev
    Next
    INDEX
    Explanations

    agonist, perennial, cardiomyopathy, enzyme

    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
    china
    -0.11
    eria
    -0.11
    ither
    -0.11
    -selector
    -0.10
    -font
    -0.10
    fts
    -0.10
    qua
    -0.10
     independ
    -0.10
    zing
    -0.09
    ft
    -0.09
    POSITIVE LOGITS
     lap
    0.09
     Cycle
    0.08
     cycle
    0.07
     bury
    0.07
     Stage
    0.07
     cycles
    0.07
     undergoing
    0.07
    nc
    0.07
    Ø°
    0.07
     recovery
    0.07
    Activations Density 0.791%

    No Known Activations