© 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. 91112
    Prev
    Next
    INDEX
    Explanations

    mental health 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
     upside
    -0.09
     sweetness
    -0.08
     reflex
    -0.08
     Situation
    -0.08
     harmless
    -0.08
     flaw
    -0.08
     pleasantly
    -0.08
    inine
    -0.08
    app
    -0.07
     transparent
    -0.07
    POSITIVE LOGITS
     depression
    0.27
     health
    0.23
     suicide
    0.22
     suicides
    0.21
     mental
    0.21
     obesity
    0.21
     Depression
    0.21
     diseases
    0.20
     premature
    0.20
     anxiety
    0.20
    Activations Density 0.820%

    No Known Activations