© 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. 34224
    Prev
    Next
    INDEX
    Explanations

    squeeze or compress

    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
     flipped
    -0.09
     scratch
    -0.09
     scratched
    -0.09
     broken
    -0.09
     smoke
    -0.08
     slash
    -0.08
     Aust
    -0.08
    cht
    -0.08
     undercut
    -0.08
     scram
    -0.08
    POSITIVE LOGITS
     squeeze
    0.32
     squeezing
    0.30
     squeezed
    0.27
     squeez
    0.26
    squeeze
    0.25
     tighter
    0.23
     tight
    0.21
     tightly
    0.19
     compress
    0.19
     Compression
    0.18
    Activations Density 0.018%

    No Known Activations