© 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. 115428
    Prev
    Next
    INDEX
    Explanations

    missed or skipped events

    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
     momentarily
    -0.11
    cid
    -0.11
     transient
    -0.11
     renting
    -0.10
     retract
    -0.10
     romant
    -0.10
    .Throw
    -0.10
    unfold
    -0.10
     distracting
    -0.10
    yan
    -0.10
    POSITIVE LOGITS
     skipped
    0.26
     missed
    0.23
     skipping
    0.21
     skip
    0.20
     Skipping
    0.19
     skips
    0.18
     consecutive
    0.18
     Skip
    0.17
     scheduled
    0.17
    skip
    0.16
    Activations Density 0.549%

    No Known Activations