© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114010
    Prev
    Next
    INDEX
    Explanations

    production or manufacturing

    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
     Lou
    -0.10
     twig
    -0.09
     warmed
    -0.09
     Dirt
    -0.09
     photography
    -0.09
     Developers
    -0.09
     photographer
    -0.09
     grass
    -0.08
     Ingredients
    -0.08
     cork
    -0.08
    POSITIVE LOGITS
     repairing
    0.13
     intricate
    0.13
     repairs
    0.12
     complicated
    0.12
     prost
    0.12
     household
    0.12
     logos
    0.12
     commissioned
    0.11
     wedding
    0.11
     projects
    0.11
    Activations Density 3.787%

    No Known Activations