© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91840
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    usch
    -0.12
     Paz
    -0.11
     preempt
    -0.11
     MART
    -0.11
     prow
    -0.10
    elas
    -0.10
    sb
    -0.10
    ."),
    -0.10
     Mills
    -0.10
     butcher
    -0.10
    POSITIVE LOGITS
    conditionally
    0.07
     Gang
    0.07
     rotten
    0.07
     Flam
    0.07
    ¼
    0.07
     ske
    0.07
    CORD
    0.07
     Gast
    0.07
    ugin
    0.07
    ought
    0.07
    Activations Density 0.000%

    No Known Activations