© 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. 32198
    Prev
    Next
    INDEX
    Explanations

    religious elements or cults

    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
     Shakespeare
    -0.13
     cowboy
    -0.10
     romance
    -0.10
     Victorian
    -0.10
     seam
    -0.10
     Romeo
    -0.10
     Patriot
    -0.10
     Romance
    -0.10
     gul
    -0.09
     Cowboy
    -0.09
    POSITIVE LOGITS
     temple
    0.34
     worsh
    0.33
     priests
    0.32
     worship
    0.32
     ritual
    0.32
     sacred
    0.31
     priest
    0.30
     sacr
    0.30
     shrine
    0.30
     consec
    0.29
    Activations Density 0.215%

    No Known Activations