© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 87661
    Prev
    Next
    INDEX
    Explanations

    making a decision

    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
    Negative Logits
     bla
    -0.10
     cogn
    -0.09
     ACE
    -0.09
    ACE
    -0.09
    eder
    -0.09
    ignore
    -0.08
    /#
    -0.08
    pline
    -0.08
    ager
    -0.08
    neh
    -0.08
    POSITIVE LOGITS
     choice
    0.32
     decision
    0.29
     chose
    0.27
     choices
    0.26
    choice
    0.25
     decisions
    0.25
     chosen
    0.25
     Choice
    0.24
     choosing
    0.24
     wisely
    0.24
    Activations Density 0.226%

    No Known Activations