© 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. 112316
    Prev
    Next
    INDEX
    Explanations

    shooting pain

    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
     body
    -0.11
    928
    -0.11
     confession
    -0.10
     precaution
    -0.10
    oux
    -0.10
    -Con
    -0.10
    Preference
    -0.10
    ocker
    -0.10
     rant
    -0.09
     psyche
    -0.09
    POSITIVE LOGITS
     pain
    0.38
     Pain
    0.30
     sensations
    0.27
     sensation
    0.25
    pain
    0.25
     discomfort
    0.23
     pains
    0.23
     feeling
    0.19
     pressure
    0.17
     agony
    0.17
    Activations Density 0.057%

    No Known Activations