© 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. 18527
    Prev
    Next
    INDEX
    Explanations

    simulate, imitation, fake, pretend

    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
     Nude
    -0.10
    uche
    -0.09
     nude
    -0.09
     Trilogy
    -0.09
     flotation
    -0.09
     Puzzle
    -0.09
     nexus
    -0.08
     uniquely
    -0.08
     Sanctuary
    -0.08
     Sculpt
    -0.08
    POSITIVE LOGITS
     pretend
    0.25
     simulated
    0.24
     fake
    0.22
     simulate
    0.22
     pretending
    0.21
     mock
    0.19
     pretended
    0.19
    pret
    0.19
     faux
    0.18
     Fake
    0.18
    Activations Density 0.464%

    No Known Activations