© 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. 18720
    Prev
    Next
    INDEX
    Explanations

    Ogden, Ogita, Olivier van

    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
    /object
    -0.16
    -orange
    -0.13
    /options
    -0.12
    /order
    -0.12
    kest
    -0.11
     Oliveira
    -0.11
    per
    -0.10
     oxide
    -0.10
    _oauth
    -0.10
    enger
    -0.10
    POSITIVE LOGITS
    entimes
    0.18
    -fashioned
    0.14
    meal
    0.14
    yssey
    0.13
    viously
    0.13
    .makedirs
    0.13
    curring
    0.12
    tober
    0.12
    ensibly
    0.12
    ahoma
    0.12
    Activations Density 1.618%

    No Known Activations