© 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. 29531
    Prev
    Next
    INDEX
    Explanations

    geckodriver, georgeous, geologic

    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
    o
    -0.15
    n
    -0.10
    e
    -0.09
    anian
    -0.09
    share
    -0.09
    r
    -0.09
    si
    -0.09
    iens
    -0.09
    do
    -0.09
    enheim
    -0.08
    POSITIVE LOGITS
    cko
    0.13
    leh
    0.12
    ographically
    0.11
    olocation
    0.11
    orgeous
    0.11
    brit
    0.11
     clo
    0.10
    issor
    0.10
    elong
    0.10
    ologic
    0.10
    Activations Density 0.015%

    No Known Activations