© 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. 116723
    Prev
    Next
    INDEX
    Explanations

    underlying conditions and 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
     fashionable
    -0.12
    HELP
    -0.10
     poisoned
    -0.10
    appen
    -0.10
     Huff
    -0.10
    ousse
    -0.10
    edriver
    -0.10
    ENV
    -0.10
    -fashion
    -0.10
    odon
    -0.10
    POSITIVE LOGITS
     conditions
    0.21
     Conditions
    0.19
     underlying
    0.18
     diseases
    0.18
    conditions
    0.17
     illnesses
    0.17
    Conditions
    0.17
     history
    0.15
     disorders
    0.14
     disabilities
    0.14
    Activations Density 1.159%

    No Known Activations