© 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. 4394
    Prev
    Next
    INDEX
    Explanations

    patients admitted to hospital

    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
     recipro
    -0.12
     seal
    -0.11
     kneeling
    -0.11
     Rubio
    -0.11
     Seal
    -0.10
     sealing
    -0.10
     Apprent
    -0.10
     VOID
    -0.10
     apprentices
    -0.10
     skype
    -0.10
    POSITIVE LOGITS
     hospital
    0.42
     Hospital
    0.33
     hospitals
    0.33
    hospital
    0.31
     hospitalized
    0.31
    Hospital
    0.28
     Hospitals
    0.27
     discharge
    0.24
    ospital
    0.23
     admission
    0.23
    Activations Density 1.199%

    No Known Activations