© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 6417
    Prev
    Next
    INDEX
    Explanations

    obedience and authority

    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
     cri
    -0.11
     wrest
    -0.11
    onden
    -0.10
     enthusi
    -0.10
     inexperienced
    -0.10
    layers
    -0.10
     definit
    -0.10
     intrig
    -0.09
     nostalg
    -0.09
     definite
    -0.09
    POSITIVE LOGITS
     superior
    0.20
     superiority
    0.20
     supremacy
    0.17
     master
    0.16
     Superior
    0.15
     authority
    0.14
     lord
    0.14
     masters
    0.14
     greatness
    0.13
     lords
    0.13
    Activations Density 0.050%

    No Known Activations