© 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. 15685
    Prev
    Next
    INDEX
    Explanations

    bowel disease and function

    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
     Mane
    -0.08
     scratched
    -0.08
     Lob
    -0.08
     Shoulder
    -0.07
     Wise
    -0.07
     ker
    -0.07
    AFF
    -0.07
     notch
    -0.07
     nail
    -0.07
     Shell
    -0.07
    POSITIVE LOGITS
     tract
    0.21
     guts
    0.15
     intest
    0.14
    intestinal
    0.14
     intestine
    0.14
     digestive
    0.14
     bowel
    0.14
    estinal
    0.13
    tract
    0.13
    ctal
    0.13
    Activations Density 0.227%

    No Known Activations