© 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. 88159
    Prev
    Next
    INDEX
    Explanations

    foreign accents

    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
     naked
    -0.11
     Nude
    -0.10
     Nom
    -0.10
     nude
    -0.10
     human
    -0.10
    Human
    -0.10
     Human
    -0.10
    inox
    -0.10
     rookies
    -0.10
     hormone
    -0.10
    POSITIVE LOGITS
     accent
    0.43
     accents
    0.38
     Accent
    0.32
    Accent
    0.28
    accent
    0.28
     dialect
    0.26
     southern
    0.20
     pronunciation
    0.18
     Southern
    0.18
     British
    0.15
    Activations Density 0.046%

    No Known Activations