© 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. 54170
    Prev
    Next
    INDEX
    Explanations

    prefix to word completion

    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
    -0.10
    gger
    -0.09
    fdf
    -0.09
     cycl
    -0.09
    isten
    -0.09
    anni
    -0.09
     ly
    -0.09
    oday
    -0.09
     ."
    -0.09
    .ib
    -0.08
    POSITIVE LOGITS
    emos
    0.09
    erton
    0.07
    Catch
    0.07
     semi
    0.07
     util
    0.07
     convers
    0.07
    READY
    0.07
     amongst
    0.07
    ail
    0.07
     neighbouring
    0.07
    Activations Density 0.069%

    No Known Activations