© 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. 26641
    Prev
    Next
    INDEX
    Explanations

    urine and bladder

    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
     cookie
    -0.12
     coc
    -0.11
     magnet
    -0.11
     Coc
    -0.11
     magnets
    -0.11
     Dust
    -0.11
    HTTPS
    -0.10
     carousel
    -0.10
     lub
    -0.10
     sed
    -0.10
    POSITIVE LOGITS
     urine
    0.48
     pee
    0.38
     urinary
    0.38
     bladder
    0.38
     Ur
    0.35
     piss
    0.30
     Pee
    0.28
     ur
    0.28
     toilet
    0.27
     ure
    0.26
    Activations Density 0.662%

    No Known Activations