© 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. 116288
    Prev
    Next
    INDEX
    Explanations

    medical/scientific contexts, especially numbers and research settings

    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
    ...↵↵↵↵
    -0.08
     brill
    -0.07
     proc
    -0.07
     perpet
    -0.07
    hsi
    -0.07
    wand
    -0.07
    ...↵↵
    -0.07
     WAY
    -0.07
    /sp
    -0.07
     denomination
    -0.07
    POSITIVE LOGITS
     Uncategorized
    0.12
     womens
    0.11
     nonsense
    0.10
     ((((
    0.10
     Unters
    0.10
    zzo
    0.10
    sitemap
    0.10
     giorn
    0.10
     ucz
    0.10
    Youtube
    0.10
    Activations Density 0.001%

    No Known Activations