© 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. 3212
    Prev
    Next
    INDEX
    Explanations

    and items in lists

    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
     Gord
    -0.09
     vice
    -0.07
    ado
    -0.07
     Kob
    -0.07
    Similarly
    -0.07
    -ro
    -0.07
     ver
    -0.07
    AMP
    -0.07
    ITT
    -0.07
    ul
    -0.06
    POSITIVE LOGITS
    /misc
    0.12
     specials
    0.12
     non
    0.11
    NY
    0.10
    _misc
    0.10
    pers
    0.10
    andin
    0.10
     ones
    0.10
    :System
    0.10
     newer
    0.10
    Activations Density 0.349%

    No Known Activations