© 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. 111379
    Prev
    Next
    INDEX
    Explanations

    decisions and choices

    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
     make
    -0.12
    making
    -0.11
    make
    -0.11
     making
    -0.11
     Make
    -0.10
     Making
    -0.10
    Make
    -0.10
    nia
    -0.10
    _make
    -0.10
     makes
    -0.10
    POSITIVE LOGITS
     mistakes
    0.21
     decisions
    0.19
     adjustments
    0.19
     mistake
    0.17
     strides
    0.16
     sacrifices
    0.16
     discoveries
    0.15
     connections
    0.15
     Connections
    0.14
     judgments
    0.13
    Activations Density 0.187%

    No Known Activations