© 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. 48358
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    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
     Lime
    -0.09
    ((-
    -0.09
     Bau
    -0.09
     favored
    -0.09
     favoured
    -0.09
    onic
    -0.08
    /games
    -0.08
     Vict
    -0.08
    —not
    -0.08
    etween
    -0.08
    POSITIVE LOGITS
     repr
    0.09
    xis
    0.09
    aza
    0.09
    {}_
    0.09
     vastly
    0.09
     Wilkinson
    0.09
     rep
    0.08
     arter
    0.08
    Entities
    0.08
     Marie
    0.08
    Activations Density 0.002%

    No Known Activations