© 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. 58940
    Prev
    Next
    INDEX
    Explanations

    new beginnings or recent occurrences

    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
     decades
    -0.18
     longstanding
    -0.15
     centuries
    -0.14
     century
    -0.14
     historically
    -0.14
     old
    -0.14
     timeless
    -0.13
     vener
    -0.13
     antiqu
    -0.13
     nostalgia
    -0.13
    POSITIVE LOGITS
     inaugural
    0.19
     debut
    0.14
     nas
    0.14
     Newly
    0.14
     newly
    0.14
     soon
    0.12
    future
    0.12
     emerging
    0.11
     rapidly
    0.11
     burgeoning
    0.11
    Activations Density 0.213%

    No Known Activations