© 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. 26663
    Prev
    Next
    INDEX
    Explanations

    depression and mood disorders

    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
     fren
    -0.13
     frantic
    -0.12
     hypocrisy
    -0.11
     panicked
    -0.11
     tolerance
    -0.11
     unten
    -0.11
     greedy
    -0.11
     frenzy
    -0.11
     nerv
    -0.10
     insanity
    -0.10
    POSITIVE LOGITS
     depressed
    0.45
     depression
    0.41
     depressive
    0.41
     depressing
    0.39
     depress
    0.36
     Depression
    0.36
     melanch
    0.35
     glo
    0.33
     mood
    0.33
     sadness
    0.31
    Activations Density 0.220%

    No Known Activations