© 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. 3583
    Prev
    Next
    INDEX
    Explanations

    yards, touchdowns, or strikeouts

    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
     consecutive
    -0.10
    loh
    -0.09
     consec
    -0.09
    ctl
    -0.09
    aman
    -0.08
    akash
    -0.08
    alent
    -0.08
    mp
    -0.08
    mock
    -0.08
     derog
    -0.08
    POSITIVE LOGITS
     Ged
    0.10
     daily
    0.09
    ubre
    0.09
     Alf
    0.09
    æĢĿ
    0.09
     cog
    0.09
    iras
    0.09
     daytime
    0.09
    grounds
    0.08
    anches
    0.08
    Activations Density 0.061%

    No Known Activations