© 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. 28777
    Prev
    Next
    INDEX
    Explanations

    engaging in activities

    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
     Chambers
    -0.10
     cyan
    -0.09
     Stamina
    -0.09
     Pawn
    -0.09
     roam
    -0.08
    rapper
    -0.08
     pelos
    -0.08
     fren
    -0.08
     stash
    -0.08
     plantation
    -0.08
    POSITIVE LOGITS
     grocery
    0.20
     shopping
    0.20
     supermarket
    0.19
     swimming
    0.18
     shower
    0.18
     driving
    0.18
     cooking
    0.16
     escal
    0.15
     restaurant
    0.15
     cook
    0.15
    Activations Density 0.210%

    No Known Activations