© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25591
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
     erót
    -0.09
    imu
    -0.09
     <![
    -0.08
     Mond
    -0.08
    ¹
    -0.08
    urch
    -0.08
     Shin
    -0.08
     Papa
    -0.08
    NR
    -0.08
     Mayor
    -0.08
    POSITIVE LOGITS
     hers
    0.17
     her
    0.14
     him
    0.14
    him
    0.13
     mine
    0.12
     me
    0.12
    å¥
    0.11
     yours
    0.11
    her
    0.11
    them
    0.11
    Activations Density 0.003%

    No Known Activations