© 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. 89134
    Prev
    Next
    INDEX
    Explanations

    Armenian and Azerbaijani contexts

    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
     Prairie
    -0.12
     Kuala
    -0.11
     Indones
    -0.11
     Pols
    -0.11
     Malaysia
    -0.11
     Midwest
    -0.11
     Malaysian
    -0.11
     Thai
    -0.10
     Indonesian
    -0.10
     Manit
    -0.10
    POSITIVE LOGITS
     Armenian
    0.39
     Armenia
    0.35
     Armen
    0.32
     Azerbaijan
    0.29
     Azerbai
    0.26
    Õ
    0.24
     Caucas
    0.18
     Georgian
    0.18
     Caucasian
    0.17
    zerbai
    0.17
    Activations Density 0.343%

    No Known Activations