© 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. 14025
    Prev
    Next
    INDEX
    Explanations

    causality and explanation

    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
    asti
    -0.10
    inely
    -0.10
    ıģ
    -0.10
    Coordinate
    -0.10
     gdb
    -0.10
    allax
    -0.10
    vendor
    -0.10
    PROP
    -0.10
     Doing
    -0.10
    hg
    -0.10
    POSITIVE LOGITS
    /ca
    0.10
     me
    0.10
     us
    0.08
     Throw
    0.08
    eso
    0.07
    arten
    0.07
    ome
    0.07
    024
    0.07
    atter
    0.07
    most
    0.07
    Activations Density 0.106%

    No Known Activations