© 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. 28570
    Prev
    Next
    INDEX
    Explanations

    Philippines and Filipino people

    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
    woods
    -0.11
    imin
    -0.10
     africa
    -0.10
    COPY
    -0.10
     Nach
    -0.10
    byss
    -0.10
    zem
    -0.10
    acular
    -0.10
     precinct
    -0.10
    Africa
    -0.10
    POSITIVE LOGITS
     Manila
    0.11
    an
    0.10
     Islands
    0.09
     Philippines
    0.09
     Filipino
    0.09
     Duterte
    0.09
     ty
    0.09
    es
    0.09
    -American
    0.09
     island
    0.08
    Activations Density 0.050%

    No Known Activations