© 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. 50985
    Prev
    Next
    INDEX
    Explanations

    reward system or rewards

    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
    woke
    -0.11
    omp
    -0.11
     pneumonia
    -0.11
    uge
    -0.11
     enclosing
    -0.11
     coffin
    -0.11
     imped
    -0.10
    cion
    -0.10
    idata
    -0.10
    avier
    -0.10
    POSITIVE LOGITS
    ingly
    0.13
    /end
    0.09
    /utility
    0.09
    swith
    0.09
    erb
    0.09
    ables
    0.08
     rewarding
    0.08
     apl
    0.08
    /fr
    0.08
     reward
    0.08
    Activations Density 0.009%

    No Known Activations