© 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. 113806
    Prev
    Next
    INDEX
    Explanations

    names containing "christ"

    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
     Toni
    -0.10
     unc
    -0.09
    Ñİ
    -0.09
     undercut
    -0.09
    able
    -0.09
     Provid
    -0.08
     wast
    -0.08
     modern
    -0.08
     annex
    -0.08
    breadcrumb
    -0.08
    POSITIVE LOGITS
    udas
    0.10
    áºŃt
    0.09
    ë¡Ŀ
    0.09
    .mx
    0.09
    awk
    0.09
    rique
    0.09
     Notice
    0.09
     Highlands
    0.09
    dar
    0.09
    rgan
    0.09
    Activations Density 0.011%

    No Known Activations