© 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. 3639
    Prev
    Next
    INDEX
    Explanations

    names with accented characters

    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
    Negative Logits
     fiance
    -0.23
     Pokemon
    -0.23
     Francois
    -0.22
     Sao
    -0.21
     Ãĥ
    -0.20
    Ãĥ
    -0.18
    Pokemon
    -0.18
    opez
    -0.17
     nao
    -0.17
     Fernandez
    -0.17
    POSITIVE LOGITS
     Pokémon
    0.24
     Québec
    0.23
     Rodr
    0.23
     MarÃŃa
    0.23
     André
    0.23
     naï
    0.23
     GarcÃŃa
    0.22
     México
    0.22
     Hawai
    0.21
     âī¤
    0.21
    Activations Density 1.483%

    No Known Activations