© 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. 15548
    Prev
    Next
    INDEX
    Explanations

    pronoun "me"

    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
    umu
    -0.10
     ought
    -0.10
     moden
    -0.10
    ather
    -0.10
     lia
    -0.10
    azen
    -0.10
    ,re
    -0.09
    iming
    -0.09
     Conway
    -0.09
     Contr
    -0.09
    POSITIVE LOGITS
    /us
    0.10
     whenever
    0.10
     anything
    0.10
     me
    0.09
     laugh
    0.09
     deja
    0.09
     about
    0.09
     anymore
    0.09
     forever
    0.09
    istar
    0.08
    Activations Density 0.002%

    No Known Activations