© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27003
    Prev
    Next
    INDEX
    Explanations

    toilets and bathrooms

    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
     wounds
    -0.09
    orde
    -0.09
     malt
    -0.08
     bruises
    -0.08
     spine
    -0.08
     bru
    -0.08
     wound
    -0.08
     toasted
    -0.08
     envelopes
    -0.08
     hobby
    -0.08
    POSITIVE LOGITS
     bathroom
    0.23
     Bathroom
    0.23
     toilet
    0.22
     bladder
    0.21
     toilets
    0.21
     urinary
    0.21
     pee
    0.20
     bathrooms
    0.20
     restroom
    0.20
     Toilet
    0.20
    Activations Density 0.060%

    No Known Activations