© 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. 112700
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by people or roles

    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
    uty
    -0.11
     infancy
    -0.10
     Guest
    -0.10
     guest
    -0.09
    ijo
    -0.09
     Guests
    -0.09
    guest
    -0.08
     graduates
    -0.08
    amen
    -0.08
     offspring
    -0.08
    POSITIVE LOGITS
     boss
    0.18
     manager
    0.14
    boss
    0.13
     bosses
    0.13
     employer
    0.13
     pastor
    0.12
     geme
    0.12
     accountant
    0.12
     doctor
    0.11
     Boss
    0.11
    Activations Density 0.098%

    No Known Activations