© 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. 18727
    Prev
    Next
    INDEX
    Explanations

    elastic tension and stretch

    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
     coats
    -0.11
    Chess
    -0.11
     solder
    -0.09
     structural
    -0.09
    atte
    -0.09
    /link
    -0.09
    enstein
    -0.09
    Defs
    -0.09
    pawn
    -0.09
    icism
    -0.09
    POSITIVE LOGITS
    elastic
    0.17
     Elastic
    0.17
     elastic
    0.17
     stretch
    0.17
     stretched
    0.17
     Rubber
    0.16
     rubber
    0.16
     bounced
    0.16
     Stretch
    0.15
     rebound
    0.14
    Activations Density 0.056%

    No Known Activations