© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50784
    Prev
    Next
    INDEX
    Explanations

    pain and discomfort descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    羨
    -0.08
    LOPT
    -0.08
    dcc
    -0.08
    antang
    -0.08
    åĨķ
    -0.08
    bserv
    -0.07
    åĪĨä¹ĭä¸Ģ
    -0.07
    å¥Ħ
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
     adm
    -0.07
    POSITIVE LOGITS
     pain
    0.16
    çĸ¼çĹĽ
    0.15
    çĸ¼
    0.13
    pain
    0.12
     Pain
    0.12
     pains
    0.11
    çĹĽ
    0.11
     sensations
    0.11
    æŃ¢çĹĽ
    0.11
     discomfort
    0.11
    Activations Density 0.077%

    No Known Activations