© 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. 26400
    Prev
    Next
    INDEX
    Explanations

    anc, Ancien, Antiqu

    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
    nore
    -0.11
    Mex
    -0.10
     aug
    -0.10
     fle
    -0.10
    Justin
    -0.10
    .Dial
    -0.10
     brows
    -0.10
    wahl
    -0.10
    asca
    -0.10
    /options
    -0.10
    POSITIVE LOGITS
     Stout
    0.09
     Ef
    0.08
    _ef
    0.08
    lood
    0.08
     TP
    0.08
    pill
    0.08
     Cassidy
    0.08
     Hugo
    0.08
     jig
    0.08
     groove
    0.08
    Activations Density 0.001%

    No Known Activations