© 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. 50322
    Prev
    Next
    INDEX
    Explanations

    repeating words or phrases

    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
    anes
    -0.09
     plots
    -0.09
     firsthand
    -0.09
     Fischer
    -0.09
     Bris
    -0.09
     Ill
    -0.08
     goose
    -0.08
     Aires
    -0.08
    aneous
    -0.08
    isle
    -0.08
    POSITIVE LOGITS
     repeating
    0.38
     repet
    0.38
     repeated
    0.37
     repetition
    0.37
     mantra
    0.37
     repetitive
    0.36
     repeats
    0.35
     repeatedly
    0.32
     repeat
    0.32
     chant
    0.32
    Activations Density 0.084%

    No Known Activations