© 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. 17102
    Prev
    Next
    INDEX
    Explanations

    trace, tracing, traceback, roots, lineage

    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
    icc
    -0.11
    odata
    -0.10
    -drive
    -0.09
     Dann
    -0.09
    _drive
    -0.09
     grips
    -0.09
     Guth
    -0.09
    ogr
    -0.09
     sneak
    -0.09
     gears
    -0.09
    POSITIVE LOGITS
     tracing
    0.26
     traced
    0.23
     trace
    0.18
     outline
    0.18
     traces
    0.18
    trace
    0.17
     tracer
    0.17
    tracer
    0.16
     outlines
    0.15
     Trace
    0.15
    Activations Density 0.038%

    No Known Activations