© 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. 91077
    Prev
    Next
    INDEX
    Explanations

    occupied

    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
     VIP
    -0.14
    VIP
    -0.11
     bedside
    -0.10
     anonymously
    -0.10
     Bethesda
    -0.10
     homic
    -0.10
     Mercer
    -0.10
     unidentified
    -0.09
     consult
    -0.09
     rigged
    -0.09
    POSITIVE LOGITS
     territory
    0.16
     conquered
    0.16
     cities
    0.16
     territories
    0.15
     northern
    0.15
     occupied
    0.15
     inland
    0.15
     marched
    0.14
     fortified
    0.14
     north
    0.13
    Activations Density 0.177%

    No Known Activations