© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50494
    Prev
    Next
    INDEX
    Explanations

    exclusive content or features

    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
     CHAPTER
    -0.11
    peg
    -0.09
     Peg
    -0.09
     BASIS
    -0.09
     pairing
    -0.09
    Chapter
    -0.09
     Chapter
    -0.08
     Appendix
    -0.08
     chapter
    -0.08
     Carousel
    -0.08
    POSITIVE LOGITS
     contents
    0.12
     Contents
    0.12
     featuring
    0.11
    exclusive
    0.10
    contents
    0.10
    pek
    0.10
     Featuring
    0.09
     exclusively
    0.09
     ONLY
    0.09
    feature
    0.09
    Activations Density 0.011%

    No Known Activations