© 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. 8894
    Prev
    Next
    INDEX
    Explanations

    workplace hierarchy and roles

    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
    Visit
    -0.10
     universities
    -0.10
     Visit
    -0.10
     Universities
    -0.09
    .Bot
    -0.09
    edu
    -0.09
    venture
    -0.09
    schools
    -0.09
     visit
    -0.09
    aky
    -0.09
    POSITIVE LOGITS
     coworkers
    0.17
     colleagues
    0.16
     supervisor
    0.16
     employee
    0.16
     department
    0.15
     bosses
    0.15
     workplace
    0.15
     Workplace
    0.14
     supervisors
    0.14
     Employee
    0.14
    Activations Density 0.449%

    No Known Activations