© 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. 90133
    Prev
    Next
    INDEX
    Explanations

    Queen Mary, Elizabeth, University

    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
    ron
    -0.07
    RON
    -0.07
    tra
    -0.07
     Breitbart
    -0.07
     spo
    -0.07
    REF
    -0.06
    adaptive
    -0.06
     vain
    -0.06
     Bureau
    -0.06
    out
    -0.06
    POSITIVE LOGITS
     Elizabeth
    0.15
    Queen
    0.14
     Queen
    0.14
    Mary
    0.14
    Elizabeth
    0.14
     Anne
    0.14
     Mary
    0.14
    hive
    0.14
     anne
    0.13
    borough
    0.13
    Activations Density 0.028%

    No Known Activations