© 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. 4260
    Prev
    Next
    INDEX
    Explanations

    code comment markers

    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
     brut
    -0.08
     eventually
    -0.08
     heck
    -0.08
    088
    -0.07
     Spartan
    -0.07
     Disqus
    -0.07
    ilyn
    -0.07
     alike
    -0.07
     periodically
    -0.07
    acos
    -0.07
    POSITIVE LOGITS
    ...↵↵↵↵
    0.11
     Junction
    0.10
     commons
    0.10
    mdi
    0.10
    \[
    0.10
     Rehab
    0.10
    tern
    0.10
     Berm
    0.10
    ..↵↵↵↵
    0.10
     !↵↵
    0.09
    Activations Density 0.135%

    No Known Activations