© 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. 8592
    Prev
    Next
    INDEX
    Explanations

    acting roles and characters

    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
     Cert
    -0.10
     orderly
    -0.10
    OCUS
    -0.10
     amat
    -0.10
    NAV
    -0.10
    ungle
    -0.10
     prominently
    -0.09
     sid
    -0.09
    inox
    -0.09
     Kidd
    -0.09
    POSITIVE LOGITS
     character
    0.15
     characterization
    0.13
     Character
    0.13
    character
    0.12
    Character
    0.11
     convincing
    0.11
     CHARACTER
    0.11
     opposite
    0.10
     vo
    0.10
     characterize
    0.10
    Activations Density 0.124%

    No Known Activations