© 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. 61376
    Prev
    Next
    INDEX
    Explanations

    educational purpose

    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
    utto
    -0.11
    orro
    -0.08
    ff
    -0.08
     brush
    -0.08
    /errors
    -0.08
    cht
    -0.08
     Liberties
    -0.08
    okie
    -0.08
    etc
    -0.07
    ood
    -0.07
    POSITIVE LOGITS
     nonprofit
    0.09
     nonprofits
    0.09
    anyl
    0.09
    iasi
    0.08
     Fever
    0.08
     lud
    0.08
    ework
    0.08
     Julien
    0.08
    reuse
    0.08
    .Directory
    0.08
    Activations Density 0.013%

    No Known Activations