© 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. 8194
    Prev
    Next
    INDEX
    Explanations

    accuracy and prediction

    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
    icas
    -0.09
    enan
    -0.08
     deed
    -0.08
    ppe
    -0.08
     OPP
    -0.08
     gew
    -0.07
     manageable
    -0.07
     Gra
    -0.07
     unstoppable
    -0.07
    Board
    -0.07
    POSITIVE LOGITS
     accuracy
    0.30
     Accuracy
    0.28
     accur
    0.24
    accuracy
    0.24
    Accuracy
    0.24
     accurate
    0.24
     inaccur
    0.23
     accurately
    0.21
     inaccurate
    0.21
    accur
    0.20
    Activations Density 0.376%

    No Known Activations