© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8900
    Prev
    Next
    INDEX
    Explanations

    during sports matches or events

    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
    Negative Logits
    hap
    -0.07
    uft
    -0.07
    ÂŃt
    -0.07
    DEST
    -0.07
     Happ
    -0.07
     CLR
    -0.06
     @}
    -0.06
    TF
    -0.06
    .book
    -0.06
    umi
    -0.06
    POSITIVE LOGITS
    iska
    0.11
     REUTERS
    0.11
    ears
    0.11
    igo
    0.10
    located
    0.09
    LOT
    0.09
     '
    0.09
    <O
    0.09
     patt
    0.09
    quisition
    0.09
    Activations Density 0.174%

    No Known Activations