© 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. 50945
    Prev
    Next
    INDEX
    Explanations

    Microsoft Corporation copyright

    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
    reeze
    -0.10
    elden
    -0.10
    anel
    -0.09
     Yong
    -0.09
    792
    -0.09
     Lynch
    -0.09
    vent
    -0.08
     outright
    -0.08
    ynch
    -0.08
     worsh
    -0.08
    POSITIVE LOGITS
    adb
    0.10
     Trot
    0.09
    _diag
    0.09
    -Language
    0.09
     Lage
    0.09
    eu
    0.08
    jos
    0.08
    825
    0.08
    wie
    0.08
    .printf
    0.08
    Activations Density 0.011%

    No Known Activations