© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10925
    Prev
    Next
    INDEX
    Explanations

    time derivative

    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
     genu
    -0.08
    ulator
    -0.07
    åIJIJ
    -0.07
    ifiz
    -0.06
    å¤ĸèµĦ
    -0.06
    ights
    -0.06
    å¾ij
    -0.06
    èĤ¡çļĦ
    -0.06
    åĽĽå¤Ħ
    -0.06
     kör
    -0.06
    POSITIVE LOGITS
    Temporal
    0.09
    åı²
    0.09
    æŶéĹ´
    0.08
    evo
    0.08
     evolution
    0.08
    _TIME
    0.08
    _time
    0.08
    edul
    0.08
    Time
    0.08
    æ¼ĶåĮĸ
    0.08
    Activations Density 0.003%

    No Known Activations