© 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. 111698
    Prev
    Next
    INDEX
    Explanations

    traps and treasures in games

    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
     Riv
    -0.08
     Emb
    -0.08
     liberty
    -0.08
     revolution
    -0.08
     eclipse
    -0.08
     Rebellion
    -0.08
    iek
    -0.07
     swo
    -0.07
     voc
    -0.07
     Gabriel
    -0.07
    POSITIVE LOGITS
     traps
    0.33
     trap
    0.27
    trap
    0.24
     treasure
    0.24
     puzzles
    0.23
     treasures
    0.23
     Trap
    0.22
    Trap
    0.20
     trapped
    0.20
     maze
    0.19
    Activations Density 0.210%

    No Known Activations