© 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. 111365
    Prev
    Next
    INDEX
    Explanations

    online shopping or travel experiences

    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
     deb
    -0.10
    antes
    -0.09
     apparent
    -0.09
    .runtime
    -0.09
    adb
    -0.08
     wre
    -0.08
     pir
    -0.08
    Ñī
    -0.08
     Sadd
    -0.08
     Ax
    -0.08
    POSITIVE LOGITS
     Ney
    0.11
     Durham
    0.10
    Cc
    0.10
    utterstock
    0.10
    thew
    0.09
    utor
    0.09
     celib
    0.09
    enames
    0.09
    wij
    0.09
    loh
    0.09
    Activations Density 0.018%

    No Known Activations