© 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. 7942
    Prev
    Next
    INDEX
    Explanations

    gift or prize

    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
    atat
    -0.10
    leh
    -0.09
    rz
    -0.09
    ymes
    -0.09
    abela
    -0.09
     giorn
    -0.09
     puss
    -0.09
     outs
    -0.09
     hopeless
    -0.09
     mailing
    -0.09
    POSITIVE LOGITS
     reward
    0.61
     rewards
    0.49
     punishment
    0.43
     Reward
    0.43
     rewarded
    0.41
    reward
    0.40
     prize
    0.38
    Reward
    0.38
     Rewards
    0.38
     compensation
    0.38
    Activations Density 0.279%

    No Known Activations