© 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. 32630
    Prev
    Next
    INDEX
    Explanations

    imaging and medical diagnosis

    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
    aler
    -0.09
     carrot
    -0.09
     datatable
    -0.09
     night
    -0.08
     balances
    -0.08
     Herz
    -0.08
     transplant
    -0.08
    licer
    -0.08
    &S
    -0.08
    ki
    -0.08
    POSITIVE LOGITS
     tid
    0.10
    zers
    0.09
     Philipp
    0.09
     Andre
    0.09
    permit
    0.09
    .Sin
    0.09
    idable
    0.09
    Andre
    0.09
     sadd
    0.09
    *size
    0.09
    Activations Density 0.002%

    No Known Activations