© 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. 17856
    Prev
    Next
    INDEX
    Explanations

    gastric cancer

    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
     wrists
    -0.12
     cerebral
    -0.12
     fracture
    -0.11
     ankles
    -0.11
     wing
    -0.11
     limb
    -0.11
     Shoulder
    -0.11
     Coal
    -0.11
     Skull
    -0.11
     neurological
    -0.11
    POSITIVE LOGITS
     stomach
    0.27
     belly
    0.25
     Belly
    0.24
     gastric
    0.23
     abdominal
    0.23
     gast
    0.22
     abdomen
    0.21
     gastro
    0.20
     digestive
    0.20
     Gast
    0.20
    Activations Density 0.572%

    No Known Activations