© 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. 32952
    Prev
    Next
    INDEX
    Explanations

    major health basic services power mineral devastating

    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
    owe
    -0.08
     covert
    -0.08
     clandest
    -0.08
     bait
    -0.07
     selfish
    -0.07
     undercover
    -0.07
     provisional
    -0.06
     Ced
    -0.06
     mojo
    -0.06
     pinch
    -0.06
    POSITIVE LOGITS
     gardening
    0.15
     parenting
    0.15
     literacy
    0.15
     geological
    0.14
     familial
    0.13
     agricultural
    0.13
    Sibling
    0.13
     sanitation
    0.13
     geopolitical
    0.13
     grammar
    0.13
    Activations Density 0.608%

    No Known Activations