© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31468
    Prev
    Next
    INDEX
    Explanations

    node.js and Alice Munro

    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
     reprodu
    -0.11
     reproduce
    -0.09
     reproduction
    -0.09
     reproduced
    -0.09
    sp
    -0.09
    lys
    -0.08
    reu
    -0.08
    liner
    -0.08
    xin
    -0.08
     Baba
    -0.08
    POSITIVE LOGITS
    -node
    0.13
    (Node
    0.13
     node
    0.13
    fieldname
    0.13
     getNode
    0.13
    .Node
    0.12
     NODE
    0.12
    js
    0.12
    /node
    0.12
     Node
    0.12
    Activations Density 0.056%

    No Known Activations