© 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. 49281
    Prev
    Next
    INDEX
    Explanations

    sewage or waste disposal

    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
     thirst
    -0.11
     bart
    -0.11
     cushions
    -0.11
     Gins
    -0.11
     Oil
    -0.11
     vapor
    -0.10
     vap
    -0.10
     Transparent
    -0.10
     oil
    -0.10
     chilling
    -0.10
    POSITIVE LOGITS
     fec
    0.45
     poop
    0.44
     dung
    0.38
     stool
    0.35
    fec
    0.35
     toilet
    0.33
     Toilet
    0.31
     bowel
    0.31
     sewage
    0.31
     toilets
    0.30
    Activations Density 0.390%

    No Known Activations