© 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. 117125
    Prev
    Next
    INDEX
    Explanations

    medicine and supplements

    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
    aten
    -0.13
     Milton
    -0.10
     RECE
    -0.10
    (dict
    -0.10
     Gale
    -0.10
     Granted
    -0.10
     loft
    -0.10
    ãĤ£
    -0.09
     Feinstein
    -0.09
    mp
    -0.09
    POSITIVE LOGITS
     pills
    0.18
     supplement
    0.13
     pill
    0.13
    -pills
    0.12
     Pills
    0.12
     supplements
    0.12
     products
    0.10
     meds
    0.10
     suppl
    0.09
     Supplement
    0.09
    Activations Density 0.021%

    No Known Activations