© 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. 8333
    Prev
    Next
    INDEX
    Explanations

    Paul followed by names

    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
    hb
    -0.08
     Transitional
    -0.08
     bump
    -0.08
    .JFrame
    -0.08
    ACP
    -0.07
    rips
    -0.07
     blink
    -0.07
    kd
    -0.07
     ty
    -0.07
    ched
    -0.07
    POSITIVE LOGITS
     Paul
    0.17
     paul
    0.17
    Paul
    0.15
     setSupportActionBar
    0.10
    .LayoutInflater
    0.10
    foreground
    0.09
    .norm
    0.09
     Paula
    0.09
     Corinthians
    0.09
     -------------
    0.09
    Activations Density 0.237%

    No Known Activations