© 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. 33716
    Prev
    Next
    INDEX
    Explanations

    performing tasks or actions

    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
     opportunities
    -0.10
     Working
    -0.10
     Opportunities
    -0.10
     Meer
    -0.10
     deadlines
    -0.10
     occasion
    -0.09
     availability
    -0.09
     atmosphere
    -0.09
     consciousness
    -0.09
     instructors
    -0.09
    POSITIVE LOGITS
     tasks
    0.25
     chores
    0.23
     feats
    0.22
     exercises
    0.20
     calculations
    0.20
     computations
    0.20
     activities
    0.20
     experiments
    0.20
     rituals
    0.19
     actions
    0.18
    Activations Density 0.936%

    No Known Activations