© 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. 50702
    Prev
    Next
    INDEX
    Explanations

    Icelandic people, places, and names

    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
     Malays
    -0.12
     Malay
    -0.12
    Äĥ
    -0.12
     buc
    -0.12
     Malaysia
    -0.11
     zam
    -0.11
     Malaysian
    -0.11
     zg
    -0.11
    ledo
    -0.10
     Kuala
    -0.10
    POSITIVE LOGITS
     Icelandic
    0.40
     Iceland
    0.38
     Rey
    0.26
    ð
    0.25
     þ
    0.23
    celand
    0.23
     Ragnar
    0.20
     ÃŃ
    0.18
     Bj
    0.18
     Greenland
    0.18
    Activations Density 0.133%

    No Known Activations