© 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. 61288
    Prev
    Next
    INDEX
    Explanations

    datasheet, product, technical article

    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
    andi
    -0.07
    abol
    -0.07
     hom
    -0.06
     mend
    -0.06
     smelled
    -0.06
     structures
    -0.06
     suff
    -0.06
     poll
    -0.06
     accepting
    -0.06
     fr
    -0.06
    POSITIVE LOGITS
     product
    0.17
     proprietary
    0.15
     manufacturer
    0.15
     Product
    0.14
     customer
    0.14
     Manuals
    0.13
    -product
    0.13
     Customer
    0.13
     supplied
    0.13
     Manufacturer
    0.13
    Activations Density 0.286%

    No Known Activations