© 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. 30950
    Prev
    Next
    INDEX
    Explanations

    Kyle and Wyatt names

    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
    obia
    -0.10
     foul
    -0.09
    rine
    -0.09
     oblig
    -0.09
    ìĹ´
    -0.08
    ensch
    -0.08
    jah
    -0.08
    asca
    -0.08
    ncia
    -0.08
    endale
    -0.08
    POSITIVE LOGITS
    eling
    0.11
    ments
    0.10
    .TestCase
    0.10
    =-=-
    0.10
    houses
    0.09
    룬
    0.09
    änd
    0.09
    itude
    0.09
    icultural
    0.09
    istani
    0.09
    Activations Density 0.493%

    No Known Activations