© 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. 55494
    Prev
    Next
    INDEX
    Explanations

    public code declarations

    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
    ante
    -0.08
     reasoned
    -0.08
    -la
    -0.08
    izer
    -0.07
     afterward
    -0.07
     occured
    -0.07
     Middleton
    -0.07
     author
    -0.07
    ulis
    -0.07
     Ter
    -0.07
    POSITIVE LOGITS
     _(
    0.11
    moz
    0.10
    .Raw
    0.10
    lix
    0.10
    );↵↵↵↵↵
    0.10
    ECH
    0.10
     Deutsch
    0.09
    aat
    0.09
    ngo
    0.09
     prest
    0.09
    Activations Density 0.015%

    No Known Activations