© 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. 111760
    Prev
    Next
    INDEX
    Explanations

    repeat / repetition

    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
    orman
    -0.11
    eld
    -0.10
     Williamson
    -0.10
     spur
    -0.10
    uckle
    -0.10
    chers
    -0.09
     Janet
    -0.09
    rov
    -0.09
    etas
    -0.09
    SCAN
    -0.09
    POSITIVE LOGITS
     repeat
    0.55
     Repeat
    0.53
     repeats
    0.52
     repeating
    0.50
    Repeat
    0.49
     repeated
    0.49
    repeat
    0.45
    -repeat
    0.38
     repetition
    0.37
    _repeat
    0.32
    Activations Density 0.363%

    No Known Activations