© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6661
    Prev
    Next
    INDEX
    Explanations

    manual labor and work

    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
    Not in Any Lists

    No Comments

    Negative Logits
     sac
    -0.10
     sacram
    -0.09
     Anita
    -0.09
     hobby
    -0.09
    slick
    -0.09
     fluffy
    -0.08
    .visit
    -0.08
     sty
    -0.08
     Funk
    -0.08
     Amateur
    -0.08
    POSITIVE LOGITS
     labor
    0.31
     labour
    0.29
     manual
    0.25
     work
    0.25
     working
    0.23
     workers
    0.22
     Labor
    0.22
     worker
    0.21
     Labour
    0.21
     hard
    0.19
    Activations Density 0.200%

    No Known Activations