© 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. 55223
    Prev
    Next
    INDEX
    Explanations

    code annotations

    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
     Filed
    -0.11
     Alive
    -0.11
    allo
    -0.10
    apper
    -0.10
     BAS
    -0.10
    uet
    -0.10
    /documentation
    -0.10
     Mellon
    -0.10
    asley
    -0.10
     indeb
    -0.10
    POSITIVE LOGITS
    gp
    0.07
    unta
    0.07
    <|endoftext|>
    0.07
     Sik
    0.06
    ↵↵↵↵
    0.06
     translucent
    0.06
    eny
    0.06
    Reviewer
    0.06
    ingly
    0.06
     console
    0.06
    Activations Density 0.003%

    No Known Activations