© 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. 58711
    Prev
    Next
    INDEX
    Explanations

    Dream Center, Heatwave, Clover Food, Invest Africa, Apache Relay, People Water

    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
     Corona
    -0.09
    irim
    -0.09
     Relief
    -0.09
     ged
    -0.09
    _drawer
    -0.09
    uffs
    -0.09
    unit
    -0.08
    listing
    -0.08
     flo
    -0.08
    (IM
    -0.08
    POSITIVE LOGITS
     themselves
    0.09
     team
    0.08
    ERA
    0.07
    elter
    0.07
     itself
    0.07
    lete
    0.07
    eras
    0.07
    quared
    0.07
    ductive
    0.07
    ails
    0.07
    Activations Density 0.038%

    No Known Activations