© 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. 7432
    Prev
    Next
    INDEX
    Explanations

    CSS properties and selectors

    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
     interactive
    -0.09
     symb
    -0.09
    erton
    -0.09
    eso
    -0.09
    erto
    -0.08
     informed
    -0.08
    _stdio
    -0.08
     bef
    -0.08
     eslint
    -0.08
     JSX
    -0.08
    POSITIVE LOGITS
     CSS
    0.16
    .css
    0.15
    Selector
    0.14
     selectors
    0.14
     css
    0.13
     Sass
    0.13
     Cascade
    0.12
     selector
    0.12
    _css
    0.12
    CSS
    0.12
    Activations Density 1.271%

    No Known Activations