© 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. 51573
    Prev
    Next
    INDEX
    Explanations

    voltage and electrical potential

    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
    æĪIJ大
    -0.07
    cket
    -0.07
    plic
    -0.07
    éĿ¢ç§¯è¾¾
    -0.07
    ProcessEvent
    -0.07
    åĶı
    -0.07
    åĩıéĩı
    -0.07
     padat
    -0.07
    æļ´é¥®
    -0.06
     foss
    -0.06
    POSITIVE LOGITS
    ç«¥
    0.09
    èĬĿ
    0.08
     volts
    0.08
    ogne
    0.08
    upi
    0.07
    oltage
    0.07
     voltage
    0.07
     Battery
    0.07
    çĶµåİĭ
    0.07
    ame
    0.07
    Activations Density 0.002%

    No Known Activations