© 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. 113402
    Prev
    Next
    INDEX
    Explanations

    decision-making

    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
     Gast
    -0.11
     hustle
    -0.08
     persist
    -0.08
     Slug
    -0.08
     plainly
    -0.08
     hust
    -0.08
    GI
    -0.08
    azi
    -0.08
    ĵ
    -0.07
     penn
    -0.07
    POSITIVE LOGITS
     decision
    0.16
    -makers
    0.15
     Decision
    0.15
    -making
    0.14
    Decision
    0.13
    decision
    0.13
     unanimous
    0.13
     choice
    0.12
     reached
    0.12
     Reached
    0.11
    Activations Density 0.071%

    No Known Activations