© 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. 92563
    Prev
    Next
    INDEX
    Explanations

    preparation tips and tactics

    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
     procession
    -0.10
     preocup
    -0.10
     perman
    -0.09
    itch
    -0.09
    Explore
    -0.09
    plorer
    -0.09
     discovering
    -0.09
     Discover
    -0.08
     SALE
    -0.08
     permanently
    -0.08
    POSITIVE LOGITS
     preparation
    0.17
     Preparation
    0.17
     tips
    0.16
    tips
    0.15
     prepar
    0.15
     Tips
    0.15
     prepared
    0.14
     preparations
    0.14
    Tips
    0.13
     tactics
    0.12
    Activations Density 0.001%

    No Known Activations