© 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. 88547
    Prev
    Next
    INDEX
    Explanations

    printing and print-related terms

    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
    /stretch
    -0.11
     Aless
    -0.10
    pek
    -0.10
     Pipes
    -0.10
    pora
    -0.10
     hus
    -0.09
     onboard
    -0.09
     Sass
    -0.09
     RTE
    -0.09
    reviews
    -0.09
    POSITIVE LOGITS
     printing
    0.49
     printed
    0.44
     Printing
    0.42
     print
    0.42
     printer
    0.40
     prints
    0.39
    -print
    0.38
     printers
    0.37
    Printing
    0.37
     Print
    0.36
    Activations Density 1.001%

    No Known Activations