© 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. 5286
    Prev
    Next
    INDEX
    Explanations

    sacred, holy, religious concepts

    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
     silhouette
    -0.09
     Sunset
    -0.09
    sons
    -0.09
     capt
    -0.09
     hooks
    -0.08
     intrig
    -0.08
    iona
    -0.08
    isko
    -0.08
    unset
    -0.08
    sembler
    -0.08
    POSITIVE LOGITS
     sanct
    0.21
     sacred
    0.18
     consec
    0.17
     holy
    0.17
     temple
    0.16
     shrine
    0.15
     secular
    0.14
     reverence
    0.14
     revered
    0.13
     worsh
    0.13
    Activations Density 0.065%

    No Known Activations