© 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. 50744
    Prev
    Next
    INDEX
    Explanations

    electrical terms and applications

    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
    ä¸įåĩı
    -0.08
    ãng
    -0.08
    ymax
    -0.08
    æľ¬å¹³åı°
    -0.07
    iggio
    -0.07
    é«ĺæ°Ķ
    -0.07
    umpt
    -0.07
    erot
    -0.07
    åĩıéĩı
    -0.07
    ellos
    -0.07
    POSITIVE LOGITS
     electrical
    0.15
     electricity
    0.13
    çĶµ
    0.13
    鼻
    0.13
     electro
    0.12
     Electrical
    0.12
     voltage
    0.12
     electric
    0.12
    çļĦçĶµ
    0.12
    çĶµåİĭ
    0.12
    Activations Density 0.154%

    No Known Activations