© 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. 117372
    Prev
    Next
    INDEX
    Explanations

    compensation, salary, bonus, fee, commission

    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
    atron
    -0.11
     embr
    -0.11
    /al
    -0.11
     Belle
    -0.10
     strides
    -0.10
    leigh
    -0.10
     Burr
    -0.10
     prices
    -0.10
    omat
    -0.10
    oft
    -0.10
    POSITIVE LOGITS
     rem
    0.13
     compensation
    0.13
     incentive
    0.12
     bonuses
    0.12
     bonus
    0.11
     compens
    0.11
     reward
    0.11
     Bonus
    0.10
     plus
    0.10
     rewarded
    0.10
    Activations Density 0.172%

    No Known Activations