© 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. 65507
    Prev
    Next
    INDEX
    Explanations

    thermodynamic and kinetic quantities like kJ mol(-1)

    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
    å¾ĹçĽĬäºİ
    -0.09
    ä¸įçĶ¨åĨį
    -0.09
     Down
    -0.08
     down
    -0.08
     xuá»ijng
    -0.08
    (down
    -0.08
     downt
    -0.08
     downs
    -0.07
    Down
    -0.07
    ä¸įæĸŃ丰å¯Į
    -0.07
    POSITIVE LOGITS
    edia
    0.08
     uphill
    0.08
    æĭĻ
    0.08
    umsuz
    0.08
    éĢĨ
    0.08
    涩
    0.08
     ÐĹаÑĤо
    0.08
    é«ĺæĺĤ
    0.08
    æĭĹ
    0.07
    ä½Ĩåı¯ä»¥
    0.07
    Activations Density 0.007%

    No Known Activations