© 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. 18158
    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
     bathroom
    -0.10
     Urdu
    -0.10
     Bathroom
    -0.08
     urinary
    -0.08
     Latin
    -0.08
     Peel
    -0.08
    .ylabel
    -0.08
     restroom
    -0.08
     nons
    -0.08
     Alo
    -0.08
    POSITIVE LOGITS
     solids
    0.14
    .JComboBox
    0.12
    <html
    0.12
    Solid
    0.11
    uros
    0.11
     !!
    0.11
     kali
    0.10
     Solid
    0.10
    ivi
    0.10
    InitialState
    0.10
    Activations Density 0.143%

    No Known Activations