© 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. 91111
    Prev
    Next
    INDEX
    Explanations

    incentive or reward phrases

    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
     greed
    -0.10
     ìĽ
    -0.09
    emes
    -0.09
     folly
    -0.09
    ane
    -0.09
     Mattis
    -0.09
    ossa
    -0.09
    alc
    -0.09
     Supply
    -0.09
     cir
    -0.09
    POSITIVE LOGITS
     incentive
    0.18
     incentiv
    0.17
     incentives
    0.17
     incent
    0.15
     compensate
    0.15
     rewarded
    0.14
     reward
    0.14
     compens
    0.13
     compensated
    0.13
     sweet
    0.12
    Activations Density 0.010%

    No Known Activations