© 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. 90266
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
     yup
    -0.08
     dodge
    -0.07
    hi
    -0.07
     tipping
    -0.07
    jar
    -0.07
    çĽ
    -0.07
    .did
    -0.07
     staffing
    -0.07
    JD
    -0.06
     germ
    -0.06
    POSITIVE LOGITS
     Excell
    0.18
     Majesty
    0.18
     Own
    0.15
    cen
    0.14
     excell
    0.14
     Emin
    0.13
     Honor
    0.13
    fault
    0.12
    izon
    0.12
    self
    0.12
    Activations Density 0.033%

    No Known Activations