© 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. 116596
    Prev
    Next
    INDEX
    Explanations

    medical conditions and symptoms

    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
    elin
    -0.08
     rigged
    -0.08
    -buttons
    -0.07
     Roe
    -0.07
     honorary
    -0.07
     repertoire
    -0.07
    brids
    -0.07
    898
    -0.07
     ignorant
    -0.07
     idiots
    -0.07
    POSITIVE LOGITS
     cravings
    0.24
     allergies
    0.24
     symptoms
    0.22
    ophobia
    0.22
     headaches
    0.21
     anxiety
    0.21
     sickness
    0.20
    itis
    0.20
     fatigue
    0.20
     confusion
    0.20
    Activations Density 1.966%

    No Known Activations