© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 57686
    Prev
    Next
    INDEX
    Explanations

    pain and comfort sensations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dim
    -0.10
    ift
    -0.09
     hyster
    -0.09
    umper
    -0.09
     taller
    -0.09
    VO
    -0.09
     ERR
    -0.09
     bmi
    -0.08
     schwar
    -0.08
     stump
    -0.08
    POSITIVE LOGITS
     discomfort
    0.16
     pain
    0.15
     unbearable
    0.14
     comfort
    0.14
     painful
    0.13
     uncomfortable
    0.13
     Pain
    0.13
     Comfort
    0.12
    Comfort
    0.12
     toler
    0.12
    Activations Density 0.129%

    No Known Activations