© 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. 8269
    Prev
    Next
    INDEX
    Explanations

    Mac followed by names or devices

    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
    itable
    -0.11
     Continental
    -0.10
    otti
    -0.09
    GRA
    -0.09
    hurst
    -0.09
     Shield
    -0.09
    ering
    -0.08
     Springs
    -0.08
    von
    -0.08
    eling
    -0.08
    POSITIVE LOGITS
    intosh
    0.20
    enzie
    0.12
    urdy
    0.12
    scopic
    0.10
    roe
    0.10
    aron
    0.10
    iej
    0.10
    beth
    0.10
     Gow
    0.09
    queen
    0.09
    Activations Density 0.161%

    No Known Activations