© 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. 4931
    Prev
    Next
    INDEX
    Explanations

    controversial / divisive subjects

    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
     adul
    -0.11
     conducive
    -0.10
     Brent
    -0.10
    Gratis
    -0.10
     incap
    -0.10
    [Index
    -0.09
    unsch
    -0.09
     empt
    -0.09
     boredom
    -0.09
     dign
    -0.09
    POSITIVE LOGITS
     controversial
    0.70
     controversy
    0.64
     controversies
    0.55
     controvers
    0.49
     contentious
    0.48
     debate
    0.46
     debated
    0.44
     Debate
    0.43
     debates
    0.42
     divisive
    0.40
    Activations Density 0.919%

    No Known Activations