© 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. 92465
    Prev
    Next
    INDEX
    Explanations

    bearing

    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
     portable
    -0.14
     Portable
    -0.13
    Portable
    -0.13
     propane
    -0.11
     fold
    -0.11
     watt
    -0.11
     sod
    -0.11
     vessel
    -0.10
     countert
    -0.10
     hydr
    -0.10
    POSITIVE LOGITS
     lubric
    0.23
     Lub
    0.19
     bearings
    0.19
     Bearings
    0.17
     bearing
    0.17
     friction
    0.15
     springs
    0.15
     groove
    0.15
     SKF
    0.15
     Bearing
    0.15
    Activations Density 4.597%

    No Known Activations