© 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. 90866
    Prev
    Next
    INDEX
    Explanations

    herbal medicine or decoction

    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
    ses
    -0.09
     upside
    -0.08
     rasp
    -0.07
    emento
    -0.07
     Tart
    -0.07
     Eisen
    -0.07
     highly
    -0.07
    Mine
    -0.07
     dum
    -0.07
    aska
    -0.07
    POSITIVE LOGITS
    prit
    0.11
     Bapt
    0.11
    ohl
    0.11
     Jacqu
    0.10
    iste
    0.10
    inki
    0.10
     unre
    0.10
    CY
    0.10
    los
    0.10
    nde
    0.10
    Activations Density 0.002%

    No Known Activations