© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18541
    Prev
    Next
    INDEX
    Explanations

    government organization rights

    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
    Negative Logits
     editorial
    -0.12
    isci
    -0.12
     Editorial
    -0.12
    åºĹ
    -0.12
     salesman
    -0.12
     firma
    -0.11
    Business
    -0.11
    business
    -0.11
    Clients
    -0.11
     business
    -0.11
    POSITIVE LOGITS
     government
    0.32
     governmental
    0.27
     Government
    0.26
    government
    0.25
    Government
    0.25
     taxpayer
    0.22
     taxpayers
    0.22
     gov
    0.21
    -government
    0.21
     bureaucrats
    0.20
    Activations Density 0.864%

    No Known Activations