© 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. 62019
    Prev
    Next
    INDEX
    Explanations

    header file includes

    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
    phem
    -0.08
    ente
    -0.08
     Stout
    -0.07
     Mist
    -0.07
     Abbott
    -0.07
     *,
    -0.07
     towards
    -0.07
     ours
    -0.07
     trump
    -0.06
    arat
    -0.06
    POSITIVE LOGITS
     Mum
    0.11
    &&!
    0.10
    panic
    0.10
     tritur
    0.10
    afb
    0.09
     Portal
    0.09
    /modal
    0.09
    iki
    0.09
    elo
    0.09
    .avatar
    0.09
    Activations Density 0.026%

    No Known Activations