© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 54927
    Prev
    Next
    INDEX
    Explanations

    religion and denomination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sacrificed
    -0.10
     Herman
    -0.09
    ICE
    -0.09
    conte
    -0.09
     Fat
    -0.09
     cann
    -0.09
     disproportion
    -0.09
     nya
    -0.08
     sacrificing
    -0.08
    Crear
    -0.08
    POSITIVE LOGITS
     religion
    0.11
     religions
    0.10
     affiliation
    0.09
     formally
    0.09
     label
    0.09
     umbrella
    0.09
     LABEL
    0.09
     affili
    0.09
     prob
    0.09
    ummy
    0.09
    Activations Density 0.042%

    No Known Activations