© 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. 47800
    Prev
    Next
    INDEX
    Explanations

    Japan and Japanese entities

    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
     Tencent
    -0.12
     dong
    -0.11
     Marseille
    -0.11
     kho
    -0.11
     Jiang
    -0.11
    jiang
    -0.11
     Lahore
    -0.10
     Dong
    -0.10
     Sind
    -0.10
     Kang
    -0.10
    POSITIVE LOGITS
     Japan
    0.30
     Japanese
    0.30
    Japan
    0.28
     japan
    0.26
    Japanese
    0.26
     japanese
    0.25
     Tokyo
    0.24
     Samurai
    0.23
     sushi
    0.23
     Fukushima
    0.22
    Activations Density 0.600%

    No Known Activations