© 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. 7095
    Prev
    Next
    INDEX
    Explanations

    pain, hurts, discomfort

    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
     divers
    -0.10
    chai
    -0.09
     Ink
    -0.09
     disciplined
    -0.09
     hypoth
    -0.09
     contamin
    -0.09
     tobacco
    -0.08
     loos
    -0.08
     Drug
    -0.08
     Vig
    -0.08
    POSITIVE LOGITS
     painful
    0.26
     pain
    0.26
     Pain
    0.25
    pain
    0.23
     discomfort
    0.19
     hurts
    0.16
     pains
    0.16
     hurting
    0.16
     uncomfortable
    0.15
     agony
    0.15
    Activations Density 0.084%

    No Known Activations