© 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. 8934
    Prev
    Next
    INDEX
    Explanations

    dimensions or lengths

    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
     Lawrence
    -0.10
     view
    -0.08
    &&(
    -0.08
    Coder
    -0.08
     instantiated
    -0.08
     real
    -0.08
    .Files
    -0.08
    keley
    -0.08
     satur
    -0.08
     Trem
    -0.08
    POSITIVE LOGITS
    lify
    0.10
    hyth
    0.09
    ylum
    0.08
     Stam
    0.08
    /+
    0.08
    wand
    0.08
     cleans
    0.08
    asts
    0.08
    dfd
    0.08
    itional
    0.07
    Activations Density 0.074%

    No Known Activations