© 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. 18694
    Prev
    Next
    INDEX
    Explanations

    -dge / -age 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
    sWith
    -0.17
    ship
    -0.16
    ly
    -0.16
    ships
    -0.15
    switch
    -0.15
    swith
    -0.15
    tings
    -0.14
    shine
    -0.14
    shape
    -0.13
    sville
    -0.13
    POSITIVE LOGITS
    able
    0.20
    y
    0.17
    (es
    0.13
    hog
    0.13
    ous
    0.12
    ãĥ£
    0.12
    ABLE
    0.12
    onor
    0.11
    orge
    0.11
    ability
    0.11
    Activations Density 0.237%

    No Known Activations