© 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. 111501
    Prev
    Next
    INDEX
    Explanations

    EX, NX, XP, XX prefixes or 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
    Negative Logits
     decl
    -0.09
     cider
    -0.09
    aket
    -0.08
    âĦ
    -0.08
     inse
    -0.08
    /groups
    -0.08
     faint
    -0.08
     acre
    -0.07
    ',(
    -0.07
     impe
    -0.07
    POSITIVE LOGITS
    ordered
    0.11
    contro
    0.10
    uent
    0.10
    enaire
    0.10
    Brandon
    0.09
    Chan
    0.09
     ventil
    0.09
    ritt
    0.09
    oku
    0.09
    xin
    0.09
    Activations Density 0.007%

    No Known Activations