© 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. 50626
    Prev
    Next
    INDEX
    Explanations

    tie or draw in scores

    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
    ubb
    -0.09
     ir
    -0.09
    kel
    -0.08
    brig
    -0.08
    chor
    -0.08
     pract
    -0.08
     bubb
    -0.08
     gratuit
    -0.08
     exaggerated
    -0.08
    rica
    -0.08
    POSITIVE LOGITS
     tie
    0.33
     evenly
    0.32
     stale
    0.30
     Tie
    0.27
     tied
    0.27
    tie
    0.26
     ties
    0.24
     deadlock
    0.22
     tying
    0.20
     equal
    0.19
    Activations Density 0.294%

    No Known Activations