© 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. 90832
    Prev
    Next
    INDEX
    Explanations

    diseases

    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
    ede
    -0.10
     protector
    -0.10
     WHO
    -0.09
    qui
    -0.09
     FDA
    -0.09
     indoors
    -0.09
    vir
    -0.09
     Ther
    -0.09
     vir
    -0.09
     posters
    -0.09
    POSITIVE LOGITS
     sy
    0.14
     tuberculosis
    0.13
     hepatitis
    0.11
     manslaughter
    0.10
     epilepsy
    0.10
     leukemia
    0.10
     pin
    0.10
     depression
    0.10
     pneumonia
    0.10
     ecstasy
    0.09
    Activations Density 0.068%

    No Known Activations