© 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. 30866
    Prev
    Next
    INDEX
    Explanations

    reduce stress 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
     Salv
    -0.14
    imit
    -0.12
     salv
    -0.11
     salvage
    -0.11
     ruined
    -0.11
    tid
    -0.10
     ruining
    -0.10
    jom
    -0.10
     causa
    -0.10
     vacations
    -0.10
    POSITIVE LOGITS
     stress
    0.30
     Stress
    0.26
    stress
    0.23
     stresses
    0.23
     stressed
    0.20
     depression
    0.19
     stressing
    0.18
     anxiety
    0.18
     pain
    0.17
     loneliness
    0.15
    Activations Density 0.145%

    No Known Activations