© 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. 8187
    Prev
    Next
    INDEX
    Explanations

    only/merely/solely

    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
     supporting
    -0.10
     ark
    -0.09
     Supporting
    -0.09
     however
    -0.08
     Wh
    -0.08
    ysi
    -0.08
    dens
    -0.08
    rit
    -0.08
    ÑĢ
    -0.08
    inz
    -0.08
    POSITIVE LOGITS
     only
    0.11
     ONLY
    0.10
    _only
    0.10
    iren
    0.10
    only
    0.10
     merely
    0.10
     ALSO
    0.09
    .debian
    0.09
     quieter
    0.09
    bor
    0.09
    Activations Density 0.466%

    No Known Activations