© 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. 58865
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    ummer
    -0.09
     pole
    -0.09
     Chap
    -0.08
    gli
    -0.08
     belt
    -0.08
    acier
    -0.08
    iland
    -0.08
    ival
    -0.08
    imore
    -0.08
     Dom
    -0.08
    POSITIVE LOGITS
    ed
    0.11
    iring
    0.09
    irim
    0.09
    es
    0.09
    iento
    0.09
    Hack
    0.09
    summ
    0.09
     OUTPUT
    0.08
    owany
    0.08
    o
    0.08
    Activations Density 0.030%

    No Known Activations