© 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. 18482
    Prev
    Next
    INDEX
    Explanations

    further disciplinary action

    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
     confusion
    -0.10
    bak
    -0.10
     misled
    -0.10
     deceived
    -0.10
     Goat
    -0.09
     distraction
    -0.09
     unrecognized
    -0.09
     PY
    -0.09
     trespass
    -0.09
     ###↵
    -0.09
    POSITIVE LOGITS
     repercussions
    0.13
     consequences
    0.13
     worse
    0.12
     punishments
    0.12
     retal
    0.11
     Worst
    0.10
     worst
    0.10
     escalated
    0.10
     punishment
    0.10
     fearing
    0.10
    Activations Density 0.001%

    No Known Activations