© 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. 8201
    Prev
    Next
    INDEX
    Explanations

    taxi medallion

    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
    ë¡ľ
    -0.11
    plat
    -0.11
    inka
    -0.10
    uni
    -0.10
    =>'
    -0.10
    ==='
    -0.09
     seh
    -0.09
    urally
    -0.09
     Pist
    -0.09
    izando
    -0.09
    POSITIVE LOGITS
    ë
    0.07
    essian
    0.07
     Vie
    0.07
     rhyme
    0.07
    ochen
    0.06
     Energ
    0.06
     getItemCount
    0.06
     Ramirez
    0.06
     Durant
    0.06
     sober
    0.06
    Activations Density 1.342%

    No Known Activations