© 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. 115317
    Prev
    Next
    INDEX
    Explanations

    with [custom/technology/jQuery/Drupal]

    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
     incest
    -0.08
    tera
    -0.08
     Millenn
    -0.07
     perfected
    -0.07
    Flush
    -0.07
     meth
    -0.07
     Milit
    -0.07
     Torch
    -0.07
     Meth
    -0.07
    iba
    -0.07
    POSITIVE LOGITS
     computers
    0.22
     numbers
    0.19
     words
    0.17
    numbers
    0.16
     horses
    0.16
     machines
    0.16
     Computers
    0.16
     manipulating
    0.16
     animals
    0.15
     Words
    0.15
    Activations Density 0.101%

    No Known Activations