© 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. 1577
    Prev
    Next
    INDEX
    Explanations

    section headers

    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
    ãĢĤ↵↵↵↵↵↵
    -0.09
     Malcolm
    -0.08
    bsites
    -0.08
    sg
    -0.07
     né
    -0.07
     fille
    -0.07
     bundle
    -0.07
    alist
    -0.07
    Extern
    -0.07
     untreated
    -0.07
    POSITIVE LOGITS
     overview
    0.13
     Conclusion
    0.12
    uat
    0.11
    overview
    0.10
     Overview
    0.10
    Conclusion
    0.10
    Uses
    0.10
    omap
    0.10
    ERRU
    0.10
     Scope
    0.10
    Activations Density 1.074%

    No Known Activations