© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 55514
    Prev
    Next
    INDEX
    Explanations

    noticed new thing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    chwitz
    -0.09
    bs
    -0.09
    bil
    -0.09
    \a
    -0.08
     genu
    -0.08
    bben
    -0.08
     advis
    -0.08
    bout
    -0.08
    fty
    -0.08
    rix
    -0.08
    POSITIVE LOGITS
     dele
    0.09
    ylie
    0.09
     worse
    0.09
     moreover
    0.08
     Rodriguez
    0.08
    yle
    0.08
     equivalent
    0.08
     Ru
    0.08
     shoppers
    0.08
     Bin
    0.08
    Activations Density 0.074%

    No Known Activations