© 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. 115673
    Prev
    Next
    INDEX
    Explanations

    Thai locations and culture

    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
     Baltimore
    -0.12
    áĥ
    -0.11
     Georgian
    -0.11
     Portugal
    -0.10
    PIO
    -0.10
     Niger
    -0.10
    oub
    -0.10
     Yosemite
    -0.10
     Dere
    -0.10
     pied
    -0.10
    POSITIVE LOGITS
     Thai
    0.28
     Bangkok
    0.27
     Thailand
    0.26
    Thai
    0.24
     thai
    0.18
     Buddha
    0.18
     Laos
    0.16
     Buddhist
    0.15
     Burma
    0.14
     Cambodia
    0.14
    Activations Density 0.040%

    No Known Activations