© 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. 115838
    Prev
    Next
    INDEX
    Explanations

    first-person possessives or objects

    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
     ourselves
    -0.12
    ve
    -0.12
    'e
    -0.11
    're
    -0.11
    ird
    -0.10
    oka
    -0.10
    ’re
    -0.10
    Tex
    -0.10
    aug
    -0.10
    tas
    -0.10
    POSITIVE LOGITS
    /us
    0.12
    coni
    0.10
    lius
    0.10
    chan
    0.10
    otti
    0.09
    cke
    0.09
     escalation
    0.09
     Cherry
    0.09
    hot
    0.08
    iosis
    0.08
    Activations Density 0.075%

    No Known Activations