© 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. 4904
    Prev
    Next
    INDEX
    Explanations

    early education and career beginnings

    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
    icht
    -0.09
     earlier
    -0.08
     revived
    -0.08
     alignments
    -0.08
     Notice
    -0.08
    Earlier
    -0.08
    anship
    -0.08
    iet
    -0.08
     truncated
    -0.08
    rays
    -0.08
    POSITIVE LOGITS
     reportedly
    0.17
     Mattis
    0.11
     "[
    0.11
     "...
    0.10
     fax
    0.10
     according
    0.10
     allegedly
    0.10
     “[
    0.09
     daily
    0.09
     Hum
    0.09
    Activations Density 0.165%

    No Known Activations