© 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. 33475
    Prev
    Next
    INDEX
    Explanations

    people in professional 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
     jails
    -0.10
    anship
    -0.10
     marriages
    -0.10
     trenches
    -0.10
    avery
    -0.10
     battleground
    -0.09
     Counties
    -0.09
     suburb
    -0.09
     Ownership
    -0.09
     dara
    -0.09
    POSITIVE LOGITS
     colleagues
    0.20
     specialists
    0.19
     peers
    0.18
     representatives
    0.18
     members
    0.18
     collaborators
    0.17
     witnesses
    0.17
     persons
    0.17
     occupants
    0.17
     personnel
    0.17
    Activations Density 3.330%

    No Known Activations