© 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. 24791
    Prev
    Next
    INDEX
    Explanations

    ATP and phosphate bonds

    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
    ebro
    -0.08
    -browser
    -0.07
    reff
    -0.07
    å¤ļåĸĿ
    -0.07
    éĢ»
    -0.07
    æłij人
    -0.07
    _browser
    -0.07
    alem
    -0.07
    å®ŀè¯Ŀ
    -0.07
     Imper
    -0.07
    POSITIVE LOGITS
     ATP
    0.10
     phosphory
    0.09
     charged
    0.08
     stored
    0.08
    åĤ¨åŃĺ
    0.08
    charged
    0.08
     bonds
    0.08
     creat
    0.08
    æ£ĺ
    0.08
     phosphate
    0.07
    Activations Density 0.037%

    No Known Activations