© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111520
    Prev
    Next
    INDEX
    Explanations

    ordering and order

    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
    Negative Logits
     Nail
    -0.10
     experiment
    -0.09
    anted
    -0.09
    _resume
    -0.09
     flooded
    -0.09
     spaced
    -0.09
    155
    -0.09
     Bud
    -0.09
     Yup
    -0.09
     planned
    -0.08
    POSITIVE LOGITS
     away
    0.14
     Ordering
    0.14
     pizza
    0.13
     ordering
    0.13
     Ordered
    0.12
     ordered
    0.12
    /order
    0.12
    ordering
    0.11
    ordered
    0.11
    /pay
    0.11
    Activations Density 0.014%

    No Known Activations