© 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. 115813
    Prev
    Next
    INDEX
    Explanations

    earning rewards or points

    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
     Localization
    -0.11
     Bans
    -0.10
     licensed
    -0.10
     Busty
    -0.10
     legalization
    -0.09
     localization
    -0.09
     convey
    -0.09
    ialis
    -0.09
     Broadcasting
    -0.09
     hover
    -0.09
    POSITIVE LOGITS
     rewards
    0.34
     Rewards
    0.33
     loyalty
    0.30
     reward
    0.28
     rewarded
    0.26
     Reward
    0.26
     Loy
    0.26
     rewarding
    0.24
     redeem
    0.22
     redemption
    0.21
    Activations Density 0.412%

    No Known Activations