© 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. 27876
    Prev
    Next
    INDEX
    Explanations

    saving money for future

    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
     requ
    -0.12
     desperation
    -0.11
     flo
    -0.11
     bell
    -0.10
     undergoing
    -0.10
     infinitely
    -0.10
    uda
    -0.10
    olver
    -0.10
    ctor
    -0.10
     reopening
    -0.10
    POSITIVE LOGITS
     savings
    0.38
     saving
    0.36
     Savings
    0.32
     Saving
    0.31
     save
    0.30
     saved
    0.29
     saves
    0.28
    Saving
    0.28
     accumulation
    0.26
     saver
    0.25
    Activations Density 0.200%

    No Known Activations