© 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. 32732
    Prev
    Next
    INDEX
    Explanations

    dates and separators

    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
     Likes
    -0.08
     mum
    -0.08
    PLUS
    -0.08
    ount
    -0.08
    edu
    -0.07
    lip
    -0.07
    illin
    -0.07
     clap
    -0.07
     shade
    -0.07
     consideration
    -0.07
    POSITIVE LOGITS
     :↵↵↵↵
    0.13
     indeb
    0.12
    ...↵↵↵↵
    0.11
    letes
    0.11
    .djang
    0.10
     Pitt
    0.10
    [Test
    0.10
    serter
    0.10
     UNUSED
    0.10
    ..↵↵↵↵
    0.10
    Activations Density 0.019%

    No Known Activations