© 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. 16147
    Prev
    Next
    INDEX
    Explanations

    organizations and providers

    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
     internals
    -0.10
     babies
    -0.10
     Guests
    -0.10
     audiences
    -0.09
     landscapes
    -0.09
    dings
    -0.09
     brides
    -0.09
     camper
    -0.09
     dues
    -0.09
     airspace
    -0.09
    POSITIVE LOGITS
     companies
    0.33
     providers
    0.31
     organizations
    0.30
     agencies
    0.27
     provider
    0.26
     suppliers
    0.26
     company
    0.25
     organisations
    0.25
     firms
    0.25
     Companies
    0.25
    Activations Density 1.061%

    No Known Activations