© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5826
    Prev
    Next
    INDEX
    Explanations

    orders and commands

    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
     Bow
    -0.09
     bä
    -0.09
    wap
    -0.09
    ITY
    -0.09
    elin
    -0.09
    FOUND
    -0.09
     houses
    -0.09
     cr
    -0.09
    zioni
    -0.09
     chooser
    -0.08
    POSITIVE LOGITS
     orders
    0.29
     commands
    0.28
     issued
    0.27
    /orders
    0.27
     directives
    0.25
     instructions
    0.23
     Orders
    0.22
    /command
    0.21
    orders
    0.21
     directions
    0.20
    Activations Density 0.194%

    No Known Activations