© 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. 8319
    Prev
    Next
    INDEX
    Explanations

    reduction and savings

    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
     Kang
    -0.08
    ilst
    -0.08
     unh
    -0.08
     stumble
    -0.08
     Gir
    -0.08
     ada
    -0.08
     Tod
    -0.08
    rary
    -0.08
     ("-
    -0.08
     acces
    -0.08
    POSITIVE LOGITS
     econom
    0.20
     savings
    0.20
     saves
    0.20
     reductions
    0.20
     saving
    0.19
     Saves
    0.19
     reduce
    0.19
     reduces
    0.19
     reducing
    0.19
     reduced
    0.19
    Activations Density 0.754%

    No Known Activations