© 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. 116981
    Prev
    Next
    INDEX
    Explanations

    pronouns for people

    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
    urge
    -0.10
     Geoff
    -0.09
     civ
    -0.09
    loff
    -0.09
     flagship
    -0.08
     Cathy
    -0.08
    anne
    -0.08
    /pop
    -0.08
    /pre
    -0.08
     Anton
    -0.08
    POSITIVE LOGITS
     scape
    0.12
    onda
    0.11
     Niet
    0.10
    andi
    0.10
     grit
    0.10
     whistle
    0.10
    èĥ½
    0.10
    azing
    0.10
    oti
    0.10
     Liqu
    0.09
    Activations Density 0.026%

    No Known Activations