© 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. 18697
    Prev
    Next
    INDEX
    Explanations

    doing manual labor

    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
     harb
    -0.13
    linger
    -0.12
     shouting
    -0.11
     married
    -0.11
     Swinger
    -0.11
     whispers
    -0.11
     Extras
    -0.11
     dreaming
    -0.11
    Extras
    -0.11
     вÑĭз
    -0.11
    POSITIVE LOGITS
     cleaning
    0.33
     Cleaning
    0.28
     repairing
    0.28
     repair
    0.26
     repairs
    0.24
    Cleaning
    0.23
     Repair
    0.21
    repair
    0.21
    Repair
    0.20
     cooking
    0.19
    Activations Density 2.061%

    No Known Activations