© 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. 8069
    Prev
    Next
    INDEX
    Explanations

    starts with "do" or "does"

    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
     doing
    -0.18
     Doing
    -0.18
    Doing
    -0.14
    doing
    -0.14
    	do
    -0.12
    åģ
    -0.12
    _do
    -0.11
    utes
    -0.11
    istica
    -0.11
    ute
    -0.11
    POSITIVE LOGITS
    cket
    0.20
    ctest
    0.19
     wonders
    0.18
    ze
    0.18
    oms
    0.17
     eiusmod
    0.17
     justice
    0.17
    le
    0.16
    zens
    0.15
    ctr
    0.14
    Activations Density 0.393%

    No Known Activations