© 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. 28521
    Prev
    Next
    INDEX
    Explanations

    business and industry types

    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
    Uber
    -0.11
    eger
    -0.10
     Carnegie
    -0.10
     Incoming
    -0.09
     briefing
    -0.09
     skype
    -0.09
     astronaut
    -0.09
     Uber
    -0.09
    CAF
    -0.09
    Official
    -0.09
    POSITIVE LOGITS
     dental
    0.17
     accounting
    0.15
     Dental
    0.14
     pharmaceutical
    0.14
     insurance
    0.14
     Accounting
    0.13
     financial
    0.13
     businesses
    0.13
     manufacturing
    0.13
     business
    0.13
    Activations Density 1.162%

    No Known Activations