© 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. 8217
    Prev
    Next
    INDEX
    Explanations

    pixel or em units

    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
     Resolution
    -0.10
    afort
    -0.10
    olu
    -0.10
     Bay
    -0.09
     ingest
    -0.09
     individual
    -0.09
    obl
    -0.09
     주
    -0.09
    reports
    -0.09
    ooke
    -0.08
    POSITIVE LOGITS
    acy
    0.09
    plr
    0.08
    /con
    0.08
     seed
    0.08
    eder
    0.08
    -cat
    0.08
    Season
    0.08
     Cascade
    0.08
     Cater
    0.08
    lor
    0.07
    Activations Density 0.058%

    No Known Activations