© 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. 3606
    Prev
    Next
    INDEX
    Explanations

    correlation between things

    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
    -ip
    -0.09
     criticisms
    -0.09
    .synthetic
    -0.09
     tuned
    -0.09
     Goldman
    -0.09
    Estimated
    -0.08
     Impl
    -0.08
     apology
    -0.08
     unrealistic
    -0.08
    ika
    -0.08
    POSITIVE LOGITS
     correlation
    0.54
     correlations
    0.46
     correl
    0.38
     association
    0.38
     linking
    0.38
     linkage
    0.38
     link
    0.38
     connection
    0.37
     caus
    0.36
     relationship
    0.36
    Activations Density 2.641%

    No Known Activations