© 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. 92144
    Prev
    Next
    INDEX
    Explanations

    owned or owning something

    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
    ior
    -0.10
     Voy
    -0.10
    iam
    -0.10
     iceberg
    -0.09
    ales
    -0.09
     Cobb
    -0.09
     traj
    -0.09
     unnoticed
    -0.09
    /as
    -0.09
    Det
    -0.09
    POSITIVE LOGITS
    (ed
    0.13
    /run
    0.11
     slaves
    0.11
    /manage
    0.10
     outright
    0.10
     guns
    0.10
     owning
    0.10
     Ow
    0.09
    aman
    0.09
     owned
    0.09
    Activations Density 0.022%

    No Known Activations