© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31461
    Prev
    Next
    INDEX
    Explanations

    Finnish or Finland related

    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
    CU
    -0.11
     Crescent
    -0.11
     carr
    -0.10
     Maced
    -0.10
     faz
    -0.10
     tej
    -0.10
     qua
    -0.10
    Bah
    -0.09
    Bins
    -0.09
     kw
    -0.09
    POSITIVE LOGITS
     Finnish
    0.52
     Finland
    0.47
     Helsinki
    0.44
    .fi
    0.37
     Finn
    0.29
     Eston
    0.29
     Nokia
    0.27
     Estonia
    0.26
     sauna
    0.24
    elsinki
    0.23
    Activations Density 1.056%

    No Known Activations