© 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. 88200
    Prev
    Next
    INDEX
    Explanations

    provinces and states

    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
     statewide
    -0.13
     locally
    -0.12
     Tehran
    -0.12
     Aleppo
    -0.12
     Beirut
    -0.12
     barang
    -0.11
     Mosul
    -0.11
     Riyadh
    -0.11
     LOCAL
    -0.10
     hele
    -0.10
    POSITIVE LOGITS
     USA
    0.29
     Australia
    0.24
     Germany
    0.23
     Canada
    0.23
     UK
    0.22
     Italy
    0.22
     India
    0.22
     Netherlands
    0.21
     England
    0.21
     Spain
    0.20
    Activations Density 1.877%

    No Known Activations