© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27048
    Prev
    Next
    INDEX
    Explanations

    European names and places with 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
    ï¼ı
    -0.09
     [...]↵↵
    -0.08
     (...
    -0.08
     Sever
    -0.08
     informat
    -0.07
    ,''
    -0.07
    ãĢĢãĢĢ
    -0.07
     Martha
    -0.07
     «
    -0.07
    agua
    -0.07
    POSITIVE LOGITS
    Ãĥ
    0.17
     Ãĥ
    0.15
    ré
    0.14
    ÃĦ
    0.14
    é
    0.13
     ÃĦ
    0.13
    %C
    0.13
     Ãħ
    0.13
    à¹ī
    0.13
     André
    0.13
    Activations Density 0.607%

    No Known Activations