© 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. 17080
    Prev
    Next
    INDEX
    Explanations

    HTML, HTML5, web development

    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
    pson
    -0.09
     Arbor
    -0.09
     amb
    -0.09
     Continent
    -0.08
     rever
    -0.08
     cryst
    -0.08
     Cardinal
    -0.08
     Desert
    -0.08
    pora
    -0.08
     sal
    -0.08
    POSITIVE LOGITS
    /XML
    0.13
    /html
    0.12
    .erb
    0.11
    ,application
    0.11
    5
    0.11
    specialchars
    0.11
    DOC
    0.11
     hyper
    0.11
    (html
    0.10
    /javascript
    0.10
    Activations Density 0.173%

    No Known Activations