© 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. 4692
    Prev
    Next
    INDEX
    Explanations

    flush toilet tank

    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
     cann
    -0.11
    ROI
    -0.11
     tum
    -0.10
     driv
    -0.10
     brut
    -0.09
    veh
    -0.09
     chest
    -0.09
     beast
    -0.09
    apos
    -0.09
     Cater
    -0.09
    POSITIVE LOGITS
     toilet
    0.35
     Toilet
    0.35
     flush
    0.28
     flushing
    0.28
     toilets
    0.27
     Flush
    0.27
     flushed
    0.25
     bathroom
    0.25
     Bathroom
    0.24
    flush
    0.23
    Activations Density 0.385%

    No Known Activations