© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33675
    Prev
    Next
    INDEX
    Explanations

    death penalty executions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     recovering
    -0.11
     skirm
    -0.10
     sidel
    -0.10
     slap
    -0.09
     mailbox
    -0.09
    ubo
    -0.09
     policing
    -0.08
     raided
    -0.08
     chasing
    -0.08
     brawl
    -0.08
    POSITIVE LOGITS
     execution
    0.38
     executions
    0.37
     Execution
    0.36
    Execution
    0.32
    execution
    0.29
     executed
    0.28
     execute
    0.27
     condemned
    0.26
     executes
    0.26
     executing
    0.26
    Activations Density 0.801%

    No Known Activations