© 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. 53763
    Prev
    Next
    INDEX
    Explanations

    data backup and recovery

    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
     Wass
    -0.10
    untas
    -0.10
     interacting
    -0.10
     allerdings
    -0.09
     prematurely
    -0.08
    azzi
    -0.08
     interactions
    -0.08
     Passing
    -0.08
     Manning
    -0.08
    Interaction
    -0.08
    POSITIVE LOGITS
     Backup
    0.13
     recovery
    0.12
     Recovery
    0.12
     backups
    0.12
     backup
    0.11
     storage
    0.11
     recover
    0.11
     ransom
    0.11
    rans
    0.11
     Storage
    0.11
    Activations Density 0.072%

    No Known Activations