© 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. 58766
    Prev
    Next
    INDEX
    Explanations

    mathematical notation involving parentheses

    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
    Ļ
    -0.09
    ents
    -0.09
    uck
    -0.08
     fle
    -0.08
     saying
    -0.08
    untas
    -0.08
    fp
    -0.08
     eighth
    -0.08
     ë°
    -0.08
    dee
    -0.08
    POSITIVE LOGITS
     Null
    0.09
     boa
    0.09
    ë
    0.09
     bo
    0.09
    ansi
    0.09
    åħ·
    0.08
    arov
    0.08
    pas
    0.08
    acha
    0.08
    isse
    0.08
    Activations Density 0.031%

    No Known Activations