© 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. 46071
    Prev
    Next
    INDEX
    Explanations

    expressing needs or beliefs

    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
     thankfully
    -0.08
     unfortunately
    -0.08
     Bernard
    -0.08
     Tee
    -0.08
     hopefully
    -0.08
     CPA
    -0.08
     alas
    -0.08
    673
    -0.08
     DJ
    -0.08
     apparently
    -0.08
    POSITIVE LOGITS
     Kendall
    0.11
     mobil
    0.11
    perf
    0.11
    aco
    0.11
    adera
    0.11
     dare
    0.10
     suff
    0.10
     nour
    0.10
     preferred
    0.09
     dispos
    0.09
    Activations Density 0.208%

    No Known Activations