© 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. 25035
    Prev
    Next
    INDEX
    Explanations

    CPU and processor specifications

    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
     Automated
    -0.11
    guarded
    -0.11
     automated
    -0.10
     embr
    -0.10
    kos
    -0.10
     situ
    -0.10
     Pitch
    -0.10
    ynet
    -0.10
    emd
    -0.10
     bedside
    -0.10
    POSITIVE LOGITS
     processor
    0.33
     CPU
    0.30
     processors
    0.29
     Processor
    0.28
     CPUs
    0.28
     RAM
    0.25
     cpu
    0.25
    CPU
    0.24
    Processor
    0.23
     GPU
    0.23
    Activations Density 1.352%

    No Known Activations