© 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. 111754
    Prev
    Next
    INDEX
    Explanations

    charting and charts.js

    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
    yat
    -0.11
    ses
    -0.10
     Rare
    -0.10
     vista
    -0.10
    hare
    -0.09
     BLE
    -0.09
    yah
    -0.09
    ArrayOf
    -0.09
    jid
    -0.09
    arme
    -0.09
    POSITIVE LOGITS
    reuse
    0.21
    /chart
    0.18
    /graph
    0.16
    .Chart
    0.14
    ing
    0.14
     chart
    0.12
     charts
    0.11
    .googleapis
    0.11
    ed
    0.11
    ulary
    0.10
    Activations Density 0.031%

    No Known Activations