© 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. 8212
    Prev
    Next
    INDEX
    Explanations

    Bob followed by names or titles

    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
     disob
    -0.12
    aub
    -0.11
    s
    -0.11
    sword
    -0.11
    .gdx
    -0.10
     Glad
    -0.10
     McGu
    -0.10
    a
    -0.10
    iad
    -0.10
    ASC
    -0.10
    POSITIVE LOGITS
    bing
    0.15
    ting
    0.12
    cat
    0.10
     bob
    0.10
     neur
    0.10
     Bellev
    0.10
     glide
    0.09
    bi
    0.09
    cats
    0.08
     Dylan
    0.08
    Activations Density 0.003%

    No Known Activations