© 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. 29944
    Prev
    Next
    INDEX
    Explanations

    layout: and DOCTYPE html

    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
     Arte
    -0.09
    /categories
    -0.09
     coherent
    -0.09
    UPI
    -0.09
    /app
    -0.09
    alley
    -0.09
     ETA
    -0.09
    keeper
    -0.08
    /icons
    -0.08
    .ACTION
    -0.08
    POSITIVE LOGITS
    forth
    0.10
    Nov
    0.10
     mole
    0.10
     patched
    0.09
     Ann
    0.09
    :b
    0.09
     adoption
    0.09
     verbally
    0.09
     toy
    0.09
     counter
    0.09
    Activations Density 0.006%

    No Known Activations