© 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. 54466
    Prev
    Next
    INDEX
    Explanations

    sports event tournament

    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
     occupancy
    -0.07
     public
    -0.07
     rehe
    -0.06
     next
    -0.06
    mom
    -0.06
    oid
    -0.06
     Schedule
    -0.06
     MOM
    -0.06
     micro
    -0.06
     cheek
    -0.06
    POSITIVE LOGITS
    apult
    0.11
    amber
    0.11
     intuit
    0.10
     tortured
    0.10
    (Spring
    0.10
    oui
    0.10
     Mär
    0.10
     decis
    0.10
    RTL
    0.10
     Juni
    0.10
    Activations Density 0.067%

    No Known Activations