© 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. 58734
    Prev
    Next
    INDEX
    Explanations

    URLs with paths and file extensions

    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
    ominator
    -0.10
    (the
    -0.10
     Además
    -0.10
    agged
    -0.09
    rax
    -0.09
    =(-
    -0.08
    —who
    -0.08
    <{
    -0.08
    concat
    -0.08
     ecology
    -0.08
    POSITIVE LOGITS
    /node
    0.10
    ansa
    0.09
    /sites
    0.08
    unu
    0.08
    weep
    0.08
     :";↵
    0.08
    821
    0.07
     closure
    0.07
    .asp
    0.07
    tee
    0.07
    Activations Density 0.060%

    No Known Activations