© 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. 4885
    Prev
    Next
    INDEX
    Explanations

    unusual rare phenomena

    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
     Pols
    -0.09
     Eld
    -0.09
     meanwhile
    -0.08
    ament
    -0.08
    lek
    -0.08
    ument
    -0.08
     miser
    -0.08
     Dumpster
    -0.08
    alysis
    -0.08
    atal
    -0.08
    POSITIVE LOGITS
     phenomenon
    0.11
     unheard
    0.11
     unusual
    0.10
     phenomena
    0.09
     rare
    0.09
     scenarios
    0.09
    unic
    0.09
     unthinkable
    0.09
     uncommon
    0.09
    dio
    0.09
    Activations Density 0.601%

    No Known Activations