© 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. 49764
    Prev
    Next
    INDEX
    Explanations

    pray, worship, knead

    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
     Reich
    -0.12
    .sleep
    -0.12
     sleep
    -0.11
     stroll
    -0.11
     ships
    -0.11
    sink
    -0.11
     swims
    -0.11
    sleep
    -0.11
     flies
    -0.11
     Railway
    -0.11
    POSITIVE LOGITS
     kneeling
    0.37
     kne
    0.25
     knees
    0.20
     worship
    0.18
     praying
    0.18
     prayer
    0.17
     worsh
    0.17
     crawling
    0.17
     knee
    0.17
     Worship
    0.17
    Activations Density 0.093%

    No Known Activations