© 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. 14031
    Prev
    Next
    INDEX
    Explanations

    joining parts or methods

    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
     liquids
    -0.14
     fluids
    -0.14
     juices
    -0.12
     spilled
    -0.12
     juice
    -0.12
     glue
    -0.11
     chemicals
    -0.11
     aque
    -0.11
     coolant
    -0.11
     liquid
    -0.10
    POSITIVE LOGITS
     hardware
    0.12
     partes
    0.11
     Hardware
    0.11
    eya
    0.11
    olut
    0.10
     lj
    0.10
     Birds
    0.10
    pii
    0.10
    Hardware
    0.10
     Bang
    0.09
    Activations Density 0.257%

    No Known Activations