© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89976
    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
     cleanup
    -0.09
     Industrial
    -0.09
    usch
    -0.09
    ango
    -0.09
    .history
    -0.09
    ANGO
    -0.09
    /history
    -0.09
     Whoever
    -0.09
     History
    -0.09
     LA
    -0.09
    POSITIVE LOGITS
     operational
    0.15
    Oper
    0.13
     operation
    0.13
    -oper
    0.13
     Modes
    0.12
     Oper
    0.12
     operations
    0.12
     operated
    0.11
    Operation
    0.11
     Operation
    0.11
    Activations Density 0.000%

    No Known Activations