© 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. 112748
    Prev
    Next
    INDEX
    Explanations

    headaches and cognitive 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
     blush
    -0.11
     ejaculation
    -0.11
     Pants
    -0.11
     freezing
    -0.10
    erek
    -0.10
     blindness
    -0.10
     Panic
    -0.10
    unic
    -0.10
     Sadd
    -0.10
     choked
    -0.10
    POSITIVE LOGITS
     headache
    0.25
     headaches
    0.21
     head
    0.19
     skull
    0.18
    /head
    0.17
     thro
    0.17
     Head
    0.17
    -head
    0.16
     brain
    0.16
     pounding
    0.16
    Activations Density 0.221%

    No Known Activations