© 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. 17841
    Prev
    Next
    INDEX
    Explanations

    owes, owing, owed, debt

    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
    olen
    -0.11
     Hits
    -0.10
    fleet
    -0.10
     belt
    -0.10
    /language
    -0.09
    belt
    -0.09
     neglect
    -0.09
     Craw
    -0.09
    burger
    -0.09
    matic
    -0.09
    POSITIVE LOGITS
     owe
    0.13
     owed
    0.13
     allegiance
    0.12
     owes
    0.10
     Deb
    0.09
     dues
    0.09
    afe
    0.08
    amon
    0.08
     owing
    0.08
    emed
    0.08
    Activations Density 0.005%

    No Known Activations