© 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. 6015
    Prev
    Next
    INDEX
    Explanations

    Hungarian months 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
     eks
    -0.10
    ifen
    -0.09
     Thr
    -0.08
     Merchant
    -0.08
     Wak
    -0.08
    esa
    -0.08
     Esc
    -0.07
     thr
    -0.07
     presup
    -0.07
    minent
    -0.07
    POSITIVE LOGITS
     Hungarian
    0.18
     Hungary
    0.15
     Budapest
    0.14
    .hu
    0.11
    ogy
    0.11
     hung
    0.10
     er
    0.10
    (cs
    0.10
     alternating
    0.10
     sz
    0.10
    Activations Density 0.001%

    No Known Activations