© 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. 8284
    Prev
    Next
    INDEX
    Explanations

    adding contrary or continuous points

    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
     fav
    -0.11
    cke
    -0.10
    udu
    -0.10
     baker
    -0.10
     finest
    -0.10
     suffice
    -0.10
    uite
    -0.10
    دÙĩ
    -0.10
     obra
    -0.10
     Yep
    -0.10
    POSITIVE LOGITS
     anyway
    0.20
     anyways
    0.18
     anyhow
    0.13
     Anyway
    0.13
    Anyway
    0.11
     furthermore
    0.11
    Furthermore
    0.11
     Plus
    0.11
     Furthermore
    0.11
     besides
    0.10
    Activations Density 0.023%

    No Known Activations