© 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. 45996
    Prev
    Next
    INDEX
    Explanations

    execution and killing

    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
    avar
    -0.10
    FAST
    -0.09
     Holt
    -0.09
    ery
    -0.09
     Mort
    -0.09
    ende
    -0.09
     startling
    -0.09
     attacks
    -0.09
     obsess
    -0.09
     Sabb
    -0.09
    POSITIVE LOGITS
     executed
    0.15
     execution
    0.13
     publicly
    0.12
     execute
    0.12
     Execute
    0.12
     executions
    0.12
     roadside
    0.11
    -exec
    0.11
    execute
    0.11
    exec
    0.11
    Activations Density 0.081%

    No Known Activations