© 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. 58864
    Prev
    Next
    INDEX
    Explanations

    decompression decompression and reverse operations

    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
     spos
    -0.10
    ign
    -0.10
    apter
    -0.10
     rub
    -0.10
    flen
    -0.10
     offs
    -0.10
    indy
    -0.10
     drastically
    -0.09
    ieber
    -0.09
    atter
    -0.09
    POSITIVE LOGITS
     restored
    0.10
     rescued
    0.10
     restores
    0.09
     resc
    0.08
     Restoration
    0.08
     authored
    0.08
     restoring
    0.08
     plac
    0.08
     warmly
    0.07
    undy
    0.07
    Activations Density 0.029%

    No Known Activations