© 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. 4969
    Prev
    Next
    INDEX
    Explanations

    protected void or override

    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
    redo
    -0.09
    bero
    -0.09
    uron
    -0.09
    ajor
    -0.09
    eler
    -0.09
    ìŀ
    -0.09
     whoever
    -0.09
     towards
    -0.08
    ran
    -0.08
    ogy
    -0.08
    POSITIVE LOGITS
     beg
    0.09
    OpenHelper
    0.08
    endet
    0.08
    /add
    0.08
    enson
    0.08
    .safe
    0.07
    <object
    0.07
     blessed
    0.07
    earch
    0.07
    ting
    0.07
    Activations Density 0.055%

    No Known Activations