© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5431
    Prev
    Next
    INDEX
    Explanations

    obey or comply

    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
     shouldn
    -0.11
    segue
    -0.11
     Respons
    -0.11
     Responsive
    -0.10
     Bur
    -0.10
     chac
    -0.10
     Pg
    -0.10
    aben
    -0.10
    Should
    -0.09
     Should
    -0.09
    POSITIVE LOGITS
     obedience
    0.14
     disobed
    0.13
     trust
    0.12
     please
    0.11
    Trust
    0.11
     obey
    0.11
     Trust
    0.11
     compliance
    0.10
     hurry
    0.10
     comply
    0.10
    Activations Density 0.079%

    No Known Activations