© 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. 29787
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by significant person/object

    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
    ande
    -0.11
    /re
    -0.11
     Nicol
    -0.10
    emer
    -0.10
    pile
    -0.10
     weighting
    -0.10
    zia
    -0.10
    versible
    -0.10
     Own
    -0.09
    /by
    -0.09
    POSITIVE LOGITS
     sworn
    0.10
    eti
    0.10
     favorite
    0.09
     guardian
    0.09
     designated
    0.09
     superior
    0.09
     hero
    0.09
     HERO
    0.09
     inspiration
    0.08
     scape
    0.08
    Activations Density 0.036%

    No Known Activations