© 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. 7126
    Prev
    Next
    INDEX
    Explanations

    owner's actions or possessions

    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
     Recru
    -0.11
     recruiting
    -0.10
    icator
    -0.09
     famine
    -0.09
    Exporter
    -0.09
    ENG
    -0.09
     replen
    -0.09
    nen
    -0.09
     pratic
    -0.09
    iken
    -0.08
    POSITIVE LOGITS
     ownership
    0.79
     Ownership
    0.67
     owning
    0.63
     owned
    0.61
     owners
    0.59
     owner
    0.59
    Ownership
    0.56
    ownership
    0.55
     owns
    0.50
     Owned
    0.50
    Activations Density 0.654%

    No Known Activations