© 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. 57916
    Prev
    Next
    INDEX
    Explanations

    version specifiers and package names

    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
    eries
    -0.11
    ered
    -0.10
    /mit
    -0.09
     [*
    -0.09
    zed
    -0.09
    alias
    -0.09
     retrospect
    -0.09
    apsible
    -0.09
     Exc
    -0.08
    ched
    -0.08
    POSITIVE LOGITS
     alternating
    0.08
    Ranked
    0.07
    prising
    0.07
     partes
    0.07
    aut
    0.07
    LOY
    0.07
    cea
    0.07
     Labour
    0.07
     totalTime
    0.07
    lyph
    0.07
    Activations Density 0.023%

    No Known Activations