© 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. 50053
    Prev
    Next
    INDEX
    Explanations

    pipe and piping

    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
     iceberg
    -0.08
     drivers
    -0.08
     Door
    -0.07
     Honda
    -0.07
     Bolton
    -0.07
    prung
    -0.07
     Vehicle
    -0.07
    amo
    -0.07
     tray
    -0.07
    edBy
    -0.07
    POSITIVE LOGITS
     pipe
    0.46
     Pipe
    0.43
     pipes
    0.43
     Pipes
    0.40
     piping
    0.38
     pip
    0.38
    pipe
    0.38
     PIPE
    0.37
     Pip
    0.37
     pipeline
    0.37
    Activations Density 0.295%

    No Known Activations