© 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. 6425
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by body parts

    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
     doorstep
    -0.12
     fleeing
    -0.11
    .Ab
    -0.10
     Inner
    -0.10
    owany
    -0.10
     folly
    -0.10
     groin
    -0.10
     Stones
    -0.10
     burgeoning
    -0.10
     clit
    -0.10
    POSITIVE LOGITS
     eyes
    0.16
     face
    0.14
     faced
    0.12
     expression
    0.12
     arms
    0.11
    eyes
    0.10
     features
    0.09
     blonde
    0.09
     faces
    0.09
     Eyes
    0.09
    Activations Density 0.016%

    No Known Activations