© 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. 49911
    Prev
    Next
    INDEX
    Explanations

    toilet flushing

    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
     multiplic
    -0.11
     TORT
    -0.11
     pinpoint
    -0.10
     rop
    -0.10
     irre
    -0.10
    pest
    -0.10
    BCM
    -0.10
     Hurt
    -0.10
     Kirk
    -0.09
     Stark
    -0.09
    POSITIVE LOGITS
     toilets
    0.10
     toilet
    0.09
     cheeks
    0.09
     Toilet
    0.08
     crimson
    0.08
     embarrassment
    0.07
    baum
    0.07
    subclass
    0.07
     fla
    0.07
     fever
    0.07
    Activations Density 0.018%

    No Known Activations