© 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. 90513
    Prev
    Next
    INDEX
    Explanations

    free software licenses

    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
    uet
    -0.10
    .dist
    -0.10
    pson
    -0.09
    esser
    -0.09
    dr
    -0.09
    ola
    -0.09
    mitt
    -0.09
    ses
    -0.08
     rouge
    -0.08
    /XML
    -0.08
    POSITIVE LOGITS
    kode
    0.10
    ipo
    0.10
     hydration
    0.09
    erdale
    0.09
     viv
    0.09
     sl
    0.08
    avan
    0.08
     dram
    0.08
     syn
    0.08
     dign
    0.08
    Activations Density 0.001%

    No Known Activations