© 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. 17911
    Prev
    Next
    INDEX
    Explanations

    times and quantities

    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
     VERIFY
    -0.10
     sunt
    -0.09
    oki
    -0.09
     being
    -0.09
    ync
    -0.09
    owy
    -0.09
    efe
    -0.09
    [${
    -0.09
    ogle
    -0.09
     problem
    -0.09
    POSITIVE LOGITS
     for
    0.14
     wisely
    0.10
     anywhere
    0.10
     daily
    0.10
     dosage
    0.10
     doses
    0.10
     as
    0.10
     sparing
    0.10
    nin
    0.10
     days
    0.10
    Activations Density 0.007%

    No Known Activations