© 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. 4712
    Prev
    Next
    INDEX
    Explanations

    log, analytics, and monitoring

    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
    Not in Any Lists

    No Comments

    Negative Logits
     publicly
    -0.08
     symbol
    -0.08
     disse
    -0.07
    qb
    -0.07
     vul
    -0.07
     orally
    -0.07
    _delegate
    -0.07
    Accessibility
    -0.07
     Cry
    -0.07
    wor
    -0.07
    POSITIVE LOGITS
     Recording
    0.14
     tracking
    0.14
     recording
    0.13
     Tracking
    0.13
     Monitoring
    0.12
    Recording
    0.12
     monitoring
    0.12
     incoming
    0.11
     Incoming
    0.11
    -monitor
    0.11
    Activations Density 0.695%

    No Known Activations