© 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. 53899
    Prev
    Next
    INDEX
    Explanations

    available without

    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
     shedding
    -0.10
    enville
    -0.09
     Nice
    -0.08
     Datum
    -0.08
     nice
    -0.08
    çļ
    -0.08
     tread
    -0.08
    ãģĺ
    -0.08
     >(
    -0.08
     shed
    -0.08
    POSITIVE LOGITS
    enschaft
    0.10
     inval
    0.09
    unt
    0.09
     Babylon
    0.08
    iq
    0.08
     dela
    0.08
    allocator
    0.08
     Ion
    0.08
     scaler
    0.08
     Daniels
    0.08
    Activations Density 0.003%

    No Known Activations