© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48060
    Prev
    Next
    INDEX
    Explanations

    staff and clientele

    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
     universities
    -0.17
     hospitals
    -0.16
     churches
    -0.14
     Universities
    -0.14
     Colleges
    -0.14
     supermarkets
    -0.14
     Schools
    -0.14
     Sites
    -0.14
     Hospitals
    -0.13
     Churches
    -0.13
    POSITIVE LOGITS
     staff
    0.30
     upstairs
    0.26
     clientele
    0.25
    staff
    0.24
     patrons
    0.24
     Staff
    0.22
     staffing
    0.22
     rooms
    0.21
    Staff
    0.21
     downstairs
    0.20
    Activations Density 0.683%

    No Known Activations