© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58912
    Prev
    Next
    INDEX
    Explanations

    energy and metabolism

    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
    Negative Logits
    óc
    -0.08
    ä¸īéĿ¢
    -0.08
    ORIA
    -0.08
    å¿ĥ声
    -0.08
    åħ¨éĥ¨è¯Ħ论
    -0.08
    øs
    -0.08
    vox
    -0.07
    uÅĤ
    -0.07
    .BorderStyle
    -0.07
     Rok
    -0.07
    POSITIVE LOGITS
     biochemical
    0.09
     phosphory
    0.09
     ATP
    0.08
     irreversible
    0.08
     metabolic
    0.08
     reversible
    0.07
     organism
    0.07
     biological
    0.07
     metabolism
    0.07
     oxidative
    0.07
    Activations Density 0.005%

    No Known Activations