© 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. 18070
    Prev
    Next
    INDEX
    Explanations

    Somali names and places

    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
     Trinidad
    -0.12
     Chile
    -0.11
     Alpine
    -0.11
     Trit
    -0.11
     Bangkok
    -0.11
     Cream
    -0.11
     Chattanooga
    -0.11
     Vish
    -0.11
     Punjab
    -0.11
     deduct
    -0.11
    POSITIVE LOGITS
     Somalia
    0.13
     Somali
    0.13
     daar
    0.12
     Mandal
    0.11
     Rohingya
    0.11
     Gamb
    0.11
     Minnesota
    0.10
     camb
    0.10
     Camb
    0.10
     Batt
    0.10
    Activations Density 0.247%

    No Known Activations