© 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. 33735
    Prev
    Next
    INDEX
    Explanations

    circadian rhythm and clock systems

    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
    åĴĢ
    -0.08
    ULK
    -0.08
     intimid
    -0.07
    "crypto
    -0.07
    udin
    -0.07
    ystack
    -0.07
    ãĥĥãĤ·ãĥ³ãĤ°
    -0.07
    anyi
    -0.07
    ×Ĺ×Ļ
    -0.07
    veloper
    -0.07
    POSITIVE LOGITS
    æĺ¼å¤ľ
    0.12
    ä½ľæģ¯
    0.10
    æĹ©çĿ¡
    0.10
    æĺ¼
    0.10
     Clock
    0.09
     clock
    0.09
     synchronized
    0.09
    Clock
    0.09
     sleep
    0.09
     sunrise
    0.09
    Activations Density 0.089%

    No Known Activations