© 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. 6196
    Prev
    Next
    INDEX
    Explanations

    bathroom locations and features

    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
     Bonds
    -0.10
     iov
    -0.09
     industri
    -0.09
     Firm
    -0.09
     bonds
    -0.09
     Blank
    -0.09
    /Peak
    -0.09
    iera
    -0.08
     Coch
    -0.08
     lub
    -0.08
    POSITIVE LOGITS
     downstairs
    0.18
     bathroom
    0.18
     bathrooms
    0.17
     toilets
    0.17
     ensuite
    0.16
     Bathroom
    0.16
     upstairs
    0.15
     plum
    0.15
     toilet
    0.15
     shared
    0.15
    Activations Density 0.166%

    No Known Activations