© 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-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16843
    Prev
    Next
    INDEX
    Explanations

    Christmas and fantasy characters

    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
     Camb
    -0.10
     Benson
    -0.10
     Vietnamese
    -0.10
     Cambodia
    -0.10
     Leopard
    -0.10
     Brut
    -0.09
    ilit
    -0.09
     Arsenal
    -0.09
     Hong
    -0.09
     Diagram
    -0.09
    POSITIVE LOGITS
     elves
    0.21
     Santa
    0.20
     rein
    0.19
     elf
    0.19
    Santa
    0.19
     Elves
    0.18
     santa
    0.17
     Elf
    0.17
    Elf
    0.16
     gnome
    0.14
    Activations Density 0.065%

    No Known Activations