© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29493
    Prev
    Next
    INDEX
    Explanations

    adjective or adverb suffixes

    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
    TER
    -0.11
    ilers
    -0.11
     und
    -0.10
     fast
    -0.10
    ells
    -0.09
    fer
    -0.09
     a
    -0.09
     (
    -0.09
    —
    -0.09
    mac
    -0.09
    POSITIVE LOGITS
    ï¸ı
    0.11
    ..↵↵↵↵
    0.11
     duk
    0.09
    /menu
    0.09
     proport
    0.09
    OrNil
    0.09
    ocre
    0.09
    !!)↵
    0.09
    edException
    0.09
     dokument
    0.09
    Activations Density 0.948%

    No Known Activations