© 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. 113101
    Prev
    Next
    INDEX
    Explanations

    making decisions or commitments

    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
     effic
    -0.10
     lucky
    -0.10
     properly
    -0.09
     Mayor
    -0.09
     Robertson
    -0.09
    jen
    -0.09
     unbelie
    -0.09
    sel
    -0.09
     SAME
    -0.09
    slick
    -0.09
    POSITIVE LOGITS
     blindly
    0.19
     any
    0.15
     finalized
    0.14
     anything
    0.14
    ä»»
    0.13
     finalize
    0.13
     rash
    0.11
     committing
    0.11
     final
    0.11
     anyone
    0.11
    Activations Density 0.043%

    No Known Activations