© 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. 89892
    Prev
    Next
    INDEX
    Explanations

    Players and receivers

    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
    morgan
    -0.12
     dime
    -0.12
    --[[
    -0.11
     Andres
    -0.11
    thouse
    -0.11
    Sidebar
    -0.11
     ($)
    -0.11
     Momentum
    -0.11
     ._
    -0.11
     Compatible
    -0.11
    POSITIVE LOGITS
    chine
    0.07
     proceeding
    0.07
     shall
    0.06
    czy
    0.06
     Clipboard
    0.06
     leg
    0.06
    Labour
    0.06
     labour
    0.06
    c
    0.06
     UIT
    0.06
    Activations Density 0.011%

    No Known Activations