© 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. 58736
    Prev
    Next
    INDEX
    Explanations

    people's positive actions and impact

    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
     periodically
    -0.09
     periodic
    -0.09
     penetr
    -0.08
     blind
    -0.08
     EVERY
    -0.08
     imperson
    -0.08
     promotional
    -0.08
     everyone
    -0.08
     grading
    -0.08
     ideal
    -0.08
    POSITIVE LOGITS
     resilience
    0.10
     diversity
    0.10
     diverse
    0.10
     extraordin
    0.09
     invent
    0.09
     ingenious
    0.09
     feats
    0.09
     Disqus
    0.09
     Diversity
    0.08
     creativity
    0.08
    Activations Density 0.096%

    No Known Activations