© 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. 91462
    Prev
    Next
    INDEX
    Explanations

    debt, loans, and bankruptcy terms

    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
     bookings
    -0.12
     Orientation
    -0.11
     Ferdinand
    -0.11
     Compensation
    -0.11
    isex
    -0.11
    upp
    -0.11
     Connectivity
    -0.11
     Ree
    -0.11
    æį®
    -0.11
     quota
    -0.11
    POSITIVE LOGITS
     Debt
    0.20
     debt
    0.20
     consolidation
    0.19
     consolid
    0.18
     consolidate
    0.17
     bankruptcy
    0.15
     creditors
    0.15
     debtor
    0.15
     refin
    0.14
     consolidated
    0.14
    Activations Density 0.595%

    No Known Activations