© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 46769
    Prev
    Next
    INDEX
    Explanations

    surgical drapes, prep, and sterile fields

    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
     exported
    -0.08
     apartment
    -0.08
     home
    -0.07
     Hier
    -0.07
     kiss
    -0.07
     Grab
    -0.07
     Rug
    -0.07
     physical
    -0.07
     claw
    -0.07
     export
    -0.07
    POSITIVE LOGITS
     HIP
    0.17
     draped
    0.13
     gown
    0.13
     Clients
    0.13
     towel
    0.13
     technician
    0.13
    /client
    0.13
     clients
    0.12
     prep
    0.12
    HIP
    0.12
    Activations Density 0.020%

    No Known Activations