© 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. 50747
    Prev
    Next
    INDEX
    Explanations

    judicial proceedings

    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
     online
    -0.18
     Virtual
    -0.16
     texting
    -0.16
     nano
    -0.16
     virtual
    -0.16
     GPS
    -0.16
     MMA
    -0.16
     internet
    -0.16
     LLC
    -0.15
     blogger
    -0.15
    POSITIVE LOGITS
    197
    0.36
    196
    0.29
     Nixon
    0.23
    198
    0.23
     disco
    0.23
     Yugosl
    0.23
     Soviet
    0.23
     USSR
    0.23
     hipp
    0.22
     Playboy
    0.21
    Activations Density 5.735%

    No Known Activations