© 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. 3543
    Prev
    Next
    INDEX
    Explanations

    e followed by common word endings

    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
    ustin
    -0.08
     blindly
    -0.08
     looping
    -0.08
     coherent
    -0.08
    irty
    -0.07
     maiden
    -0.07
     Kes
    -0.07
    elter
    -0.07
    itor
    -0.07
     rut
    -0.07
    POSITIVE LOGITS
     ect
    0.14
     eyebrow
    0.13
    /e
    0.13
     elong
    0.12
     edge
    0.12
     Ink
    0.12
     agon
    0.12
     EDGE
    0.12
     encyclopedia
    0.12
     envelope
    0.12
    Activations Density 0.080%

    No Known Activations