© 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. 8740
    Prev
    Next
    INDEX
    Explanations

    disclosed in patents

    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
    etable
    -0.11
    ahoma
    -0.11
     shown
    -0.11
     Table
    -0.11
    shown
    -0.10
    Table
    -0.10
    antha
    -0.10
     Shutterstock
    -0.10
    ycin
    -0.10
     heading
    -0.10
    POSITIVE LOGITS
     Official
    0.07
     Seat
    0.07
     fleet
    0.07
    Ú©
    0.06
    beam
    0.06
    inx
    0.06
     dazz
    0.06
    /world
    0.06
     Mand
    0.06
    /books
    0.06
    Activations Density 0.099%

    No Known Activations