© 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. 89820
    Prev
    Next
    INDEX
    Explanations

    borrowing money

    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
     laz
    -0.14
     lazy
    -0.13
     antid
    -0.12
    tid
    -0.10
     detached
    -0.10
     overpower
    -0.10
     Geh
    -0.10
     tid
    -0.10
    lazy
    -0.10
     Hod
    -0.10
    POSITIVE LOGITS
     ration
    0.19
     borrowing
    0.19
     borrow
    0.17
     starvation
    0.16
     scrim
    0.16
    borrow
    0.16
     pawn
    0.15
     borrowed
    0.15
     desperation
    0.15
     resort
    0.15
    Activations Density 0.361%

    No Known Activations