© 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. 61344
    Prev
    Next
    INDEX
    Explanations

    precision and accuracy

    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
     thresh
    -0.10
    ë¡Ŀ
    -0.09
    ault
    -0.09
     æ¸
    -0.09
    /assert
    -0.09
    olu
    -0.09
    üler
    -0.09
     fuck
    -0.09
     capture
    -0.09
    .Namespace
    -0.09
    POSITIVE LOGITS
    peace
    0.09
    jsc
    0.08
     peace
    0.08
     Wall
    0.08
     laid
    0.07
     fav
    0.07
     sed
    0.07
     vice
    0.07
     routine
    0.07
    ints
    0.07
    Activations Density 0.020%

    No Known Activations