© 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. 8574
    Prev
    Next
    INDEX
    Explanations

    ATP production and synthesis

    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
    noinspection
    -0.08
    é£ŀåĪ©æµ¦
    -0.07
    stä
    -0.07
    اشت
    -0.07
    áºłI
    -0.06
    è¡Ģä¸Ŀ
    -0.06
    ÑĤивÑĥ
    -0.06
    InView
    -0.06
    à¸Ķย
    -0.06
     khuất
    -0.06
    POSITIVE LOGITS
    igue
    0.09
    Ø©
    0.08
    ases
    0.08
    ickle
    0.08
    ãĤĪãģĨãģª
    0.07
    imana
    0.07
    ç»Ĩèĥŀ
    0.07
     ATP
    0.07
    izz
    0.07
    äºĨæĸ°
    0.07
    Activations Density 0.019%

    No Known Activations