© 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. 32273
    Prev
    Next
    INDEX
    Explanations

    buying goods and services

    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
     spills
    -0.11
     Gameplay
    -0.10
     upside
    -0.10
     motto
    -0.09
     Petty
    -0.09
     Drawer
    -0.09
    essler
    -0.09
     Voc
    -0.09
     wearer
    -0.09
    izando
    -0.09
    POSITIVE LOGITS
     goods
    0.27
     merchandise
    0.26
     tickets
    0.26
     supplies
    0.26
     products
    0.25
     groceries
    0.24
     subscriptions
    0.22
    goods
    0.22
     purch
    0.21
     purchases
    0.20
    Activations Density 1.538%

    No Known Activations