© 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. 28834
    Prev
    Next
    INDEX
    Explanations

    country names after "of"

    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
     cities
    -0.11
    cities
    -0.11
     statewide
    -0.11
     Cities
    -0.10
     Paris
    -0.10
    ikal
    -0.10
    Paris
    -0.10
     Tokyo
    -0.10
    Cities
    -0.10
    elon
    -0.09
    POSITIVE LOGITS
     United
    0.13
    United
    0.12
     UNITED
    0.11
     USA
    0.11
    USA
    0.10
    hana
    0.09
     US
    0.09
     pots
    0.09
     united
    0.09
     Usa
    0.09
    Activations Density 0.047%

    No Known Activations