© 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. 24970
    Prev
    Next
    INDEX
    Explanations

    real-world scenarios

    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
    /watch
    -0.10
    CommandLine
    -0.10
     rethink
    -0.09
     lifestyle
    -0.09
     kang
    -0.08
    们
    -0.08
     Crosby
    -0.08
     halftime
    -0.08
     spirit
    -0.08
    368
    -0.08
    POSITIVE LOGITS
     counterparts
    0.16
     situations
    0.15
     counterpart
    0.15
     equivalents
    0.14
     scenarios
    0.13
     situation
    0.12
     examples
    0.12
    (real
    0.12
     scenario
    0.11
     implications
    0.11
    Activations Density 0.117%

    No Known Activations