© 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. 49365
    Prev
    Next
    INDEX
    Explanations

    Taiwan

    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
     Ùĥ
    -0.12
    Ùĥ
    -0.11
    们
    -0.10
    ÙĬ
    -0.10
    acl
    -0.10
    éķ¿
    -0.10
     Somali
    -0.10
     Mate
    -0.10
    æŶ
    -0.10
     ÙĬ
    -0.09
    POSITIVE LOGITS
     Taiwanese
    0.35
     Taiwan
    0.35
     Taipei
    0.31
    Tai
    0.28
    åı°
    0.23
     tai
    0.23
    .tw
    0.18
     Tai
    0.15
     tvb
    0.15
    å¾Į
    0.13
    Activations Density 0.567%

    No Known Activations