© 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. 87609
    Prev
    Next
    INDEX
    Explanations

    -wide, -wider, -widest, -widely

    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
    Priv
    -0.13
     Priv
    -0.12
    allen
    -0.12
    ikal
    -0.11
     tarn
    -0.11
     Lawrence
    -0.11
    commission
    -0.11
     Cow
    -0.11
     unpack
    -0.11
    TEE
    -0.11
    POSITIVE LOGITS
     wide
    0.14
     slightly
    0.12
     wider
    0.11
    -wide
    0.09
    ned
    0.09
     widest
    0.09
     to
    0.08
    ed
    0.08
    ted
    0.07
     widely
    0.07
    Activations Density 0.003%

    No Known Activations