© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 46322
    Prev
    Next
    INDEX
    Explanations

    italian and french locations or 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
     Australian
    -0.11
    Australian
    -0.09
     Aussie
    -0.09
     kitt
    -0.08
     Rodr
    -0.08
    rá
    -0.08
    kov
    -0.08
     FBI
    -0.08
    ÃŃa
    -0.08
     Smithsonian
    -0.08
    POSITIVE LOGITS
     gratuit
    0.16
     Lyon
    0.14
     gratis
    0.12
    yon
    0.12
     Alger
    0.11
     Tunis
    0.11
     proximity
    0.11
     France
    0.11
     Belg
    0.11
     urg
    0.11
    Activations Density 0.017%

    No Known Activations