© 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. 29914
    Prev
    Next
    INDEX
    Explanations

    medication and treatment

    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
     Dixon
    -0.09
     sting
    -0.09
    atra
    -0.09
     cubes
    -0.09
     Basket
    -0.09
     wings
    -0.08
     Lounge
    -0.08
     Cah
    -0.08
     pointers
    -0.08
     VIP
    -0.08
    POSITIVE LOGITS
     medication
    0.59
     medications
    0.57
     meds
    0.46
     medicines
    0.46
     drugs
    0.43
     Medic
    0.42
     antibiotics
    0.41
     medic
    0.38
     pharmaceutical
    0.38
     antidepress
    0.37
    Activations Density 1.679%

    No Known Activations