© 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. 46606
    Prev
    Next
    INDEX
    Explanations

    contiguous U.S. states and countries

    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
    vest
    -0.10
     hauling
    -0.10
    isha
    -0.10
     Hyde
    -0.10
    omen
    -0.09
    iku
    -0.09
     loan
    -0.09
    .Alignment
    -0.09
     Beng
    -0.09
    unny
    -0.09
    POSITIVE LOGITS
     customers
    0.16
     mainland
    0.15
     territories
    0.14
     contiguous
    0.14
     territory
    0.13
    customers
    0.12
     Customers
    0.12
     residents
    0.11
     territorial
    0.11
     excl
    0.10
    Activations Density 0.346%

    No Known Activations