© 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. 57515
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
    ford
    -0.09
     Sed
    -0.09
     sed
    -0.08
    enton
    -0.08
     nurs
    -0.08
    atham
    -0.08
    phis
    -0.08
     hourly
    -0.08
    taire
    -0.08
    efe
    -0.08
    POSITIVE LOGITS
    CMS
    0.09
     leveling
    0.08
    ä½ľ
    0.08
    ython
    0.08
    stile
    0.08
    ~-
    0.08
    unger
    0.08
    ients
    0.08
    alte
    0.08
    thon
    0.08
    Activations Density 0.059%

    No Known Activations