© 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. 30574
    Prev
    Next
    INDEX
    Explanations

    Catalan and Barcelona 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
     Tehran
    -0.13
     Iranian
    -0.11
     Midlands
    -0.11
    bine
    -0.10
     Derby
    -0.10
     Alma
    -0.10
     Worce
    -0.10
     Kansas
    -0.10
     Yemen
    -0.10
     Kabul
    -0.10
    POSITIVE LOGITS
     Catalan
    0.31
     Barcelona
    0.31
     Catalonia
    0.30
     barcelona
    0.24
     Catal
    0.19
     Jord
    0.19
     ÃĢ
    0.18
    celona
    0.18
    Ãł
    0.17
     catal
    0.17
    Activations Density 0.384%

    No Known Activations