© 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. 117613
    Prev
    Next
    INDEX
    Explanations

    Mod followed by certain 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
    umbing
    -0.10
     bore
    -0.10
    quals
    -0.10
    ipel
    -0.10
    alles
    -0.10
    iland
    -0.09
    ubber
    -0.09
    UGIN
    -0.09
    concert
    -0.09
    bum
    -0.09
    POSITIVE LOGITS
    ded
    0.14
    ifiable
    0.11
    ding
    0.11
     Mod
    0.11
    ifying
    0.11
     mod
    0.11
    ders
    0.10
    ifi
    0.09
    ifies
    0.09
     Tec
    0.09
    Activations Density 0.018%

    No Known Activations