© 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. 27709
    Prev
    Next
    INDEX
    Explanations

    money and greed

    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
     refund
    -0.12
    refund
    -0.11
     costs
    -0.10
     unpaid
    -0.10
     shaved
    -0.10
     costing
    -0.10
     subsidized
    -0.10
     subsid
    -0.10
     deduct
    -0.10
     refunds
    -0.10
    POSITIVE LOGITS
     greed
    0.18
     Money
    0.15
     material
    0.14
     motivating
    0.14
     Material
    0.14
     corrupt
    0.13
    Money
    0.13
     MONEY
    0.13
     chase
    0.13
     money
    0.13
    Activations Density 0.183%

    No Known Activations