© 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. 114333
    Prev
    Next
    INDEX
    Explanations

    JC Penney, Rutherford, Power, Media, News

    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
     conspic
    -0.09
    aaS
    -0.09
     Tribe
    -0.09
     inse
    -0.09
     Malone
    -0.08
     acc
    -0.08
     HEAP
    -0.08
     preempt
    -0.08
    ardon
    -0.08
    :maj
    -0.08
    POSITIVE LOGITS
     UM
    0.10
    æĻ¯
    0.09
     strap
    0.08
     Calvin
    0.08
     BMP
    0.08
    otte
    0.08
     skept
    0.08
    inois
    0.08
    itect
    0.08
    bach
    0.08
    Activations Density 0.296%

    No Known Activations