© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49308
    Prev
    Next
    INDEX
    Explanations

    corporate and executive roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     technician
    -0.14
     payroll
    -0.14
     tavern
    -0.13
     locksmith
    -0.13
     backlog
    -0.13
     artisan
    -0.13
     technicians
    -0.13
     Customers
    -0.13
     milit
    -0.13
     shop
    -0.13
    POSITIVE LOGITS
     corporate
    0.18
     executive
    0.18
     executives
    0.17
     MBA
    0.16
     Corporate
    0.16
     exec
    0.16
     CEO
    0.15
     CEOs
    0.15
     Exec
    0.14
     merg
    0.14
    Activations Density 0.249%

    No Known Activations