© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8238
    Prev
    Next
    INDEX
    Explanations

    crimes against humanity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     insol
    -0.11
    éĻ
    -0.10
     quitting
    -0.09
     sabot
    -0.09
    .ham
    -0.09
     tou
    -0.09
    FTA
    -0.09
     POS
    -0.09
     conspir
    -0.08
     loaf
    -0.08
    POSITIVE LOGITS
     executions
    0.15
     cruelty
    0.13
     killing
    0.13
     killings
    0.13
    ocide
    0.12
     scor
    0.12
     Cru
    0.12
     roundup
    0.11
     humane
    0.11
     cru
    0.11
    Activations Density 0.278%

    No Known Activations