© 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. 112605
    Prev
    Next
    INDEX
    Explanations

    cleaning and sanitizing products

    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
     Bris
    -0.11
     Horton
    -0.11
     ero
    -0.11
     butter
    -0.10
     dripping
    -0.09
    umm
    -0.08
     Nath
    -0.08
     worn
    -0.08
     cort
    -0.08
    lose
    -0.08
    POSITIVE LOGITS
     Cleaner
    0.14
     cleaner
    0.12
     sanit
    0.12
     upkeep
    0.12
     cleansing
    0.11
     sanitizer
    0.11
     cleaning
    0.11
     wipes
    0.11
     Cleans
    0.11
     cleanup
    0.10
    Activations Density 0.074%

    No Known Activations