© 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. 90256
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by related people or things

    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
    /exp
    -0.11
     unb
    -0.11
     Wife
    -0.10
     darn
    -0.10
     Bark
    -0.10
     Nash
    -0.10
    ordes
    -0.10
     minds
    -0.10
    kee
    -0.10
    Brains
    -0.10
    POSITIVE LOGITS
     friends
    0.15
     acquaint
    0.13
     relatives
    0.13
     coworkers
    0.13
     classmates
    0.12
     ancestors
    0.11
     peers
    0.11
     colleagues
    0.10
     predecessors
    0.10
     belongings
    0.10
    Activations Density 0.078%

    No Known Activations