© 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. 26637
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or apostrophes

    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
     face
    -0.12
     complication
    -0.12
     circumstance
    -0.12
     Lives
    -0.11
     abdomen
    -0.11
     ordeal
    -0.11
     eyes
    -0.11
     preval
    -0.11
     hands
    -0.11
     eyebrows
    -0.11
    POSITIVE LOGITS
     deepest
    0.12
     wil
    0.12
     darkest
    0.11
     worst
    0.11
    iest
    0.11
     finest
    0.10
     Dee
    0.10
     most
    0.10
     innate
    0.10
     various
    0.09
    Activations Density 0.059%

    No Known Activations