© 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. 16276
    Prev
    Next
    INDEX
    Explanations

    rules for communities

    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
     campuses
    -0.11
     Committees
    -0.10
     internet
    -0.10
     cho
    -0.10
     Repos
    -0.09
    _blog
    -0.09
     Blogs
    -0.09
     colonies
    -0.09
    _clusters
    -0.09
     compartments
    -0.09
    POSITIVE LOGITS
     rules
    0.18
     moderator
    0.18
     members
    0.18
     Rules
    0.17
     posts
    0.17
     moderators
    0.17
     moderation
    0.16
     pinned
    0.15
    rules
    0.15
     Moder
    0.15
    Activations Density 0.302%

    No Known Activations