© 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. 8832
    Prev
    Next
    INDEX
    Explanations

    emphasizing "really"

    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
    羣
    -0.11
     actually
    -0.11
    ities
    -0.10
     Slim
    -0.10
     actual
    -0.10
    ett
    -0.10
    cci
    -0.10
    actually
    -0.09
    _callable
    -0.09
     Strom
    -0.09
    POSITIVE LOGITS
     shouldn
    0.09
    esen
    0.08
     focusing
    0.07
     shine
    0.07
     focus
    0.07
     outstanding
    0.07
     ought
    0.07
    visa
    0.07
    wig
    0.07
     should
    0.07
    Activations Density 0.053%

    No Known Activations