© 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. 53837
    Prev
    Next
    INDEX
    Explanations

    any followed by request for help or suggestions

    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
    agogue
    -0.09
     Disqus
    -0.09
     scorer
    -0.09
    anova
    -0.09
    oops
    -0.09
     Familie
    -0.09
    pard
    -0.09
    una
    -0.09
    perator
    -0.09
    ailing
    -0.08
    POSITIVE LOGITS
     anywhere
    0.08
     recommendations
    0.08
     special
    0.08
     Mou
    0.08
    иÑħ
    0.08
     invert
    0.08
    ugg
    0.08
    ongs
    0.08
     suggestions
    0.08
     пов
    0.08
    Activations Density 0.059%

    No Known Activations