© 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. 111696
    Prev
    Next
    INDEX
    Explanations

    library files and extensions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    developers
    -0.12
     IntelliJ
    -0.12
    Servlet
    -0.11
    _Server
    -0.11
    Software
    -0.11
     postfix
    -0.11
     runnable
    -0.11
    Hosting
    -0.11
    developer
    -0.11
     lambda
    -0.10
    POSITIVE LOGITS
     library
    0.16
    lib
    0.15
     lib
    0.13
    åºĵ
    0.13
     utilities
    0.13
     package
    0.12
     Library
    0.11
     Lib
    0.11
    _strerror
    0.11
     convenience
    0.11
    Activations Density 9.001%

    No Known Activations