© 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. 29060
    Prev
    Next
    INDEX
    Explanations

    electrical potential difference

    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
    æ¶ĪåĮĸçļĦ
    -0.08
    å¯ħ
    -0.08
     tonn
    -0.08
    Ú¯ÛĮر
    -0.08
    à¹ĥหà¸įà¹Ī
    -0.08
    ãĥ¼ãĥķ
    -0.08
    ¿
    -0.07
    æ¶ĪåĮĸ
    -0.07
    à´ķàµįà´·
    -0.07
    _tail
    -0.07
    POSITIVE LOGITS
     gradient
    0.09
    梯度
    0.08
     electrical
    0.08
     electric
    0.08
     voltage
    0.08
    gradient
    0.08
     junction
    0.08
     volts
    0.08
    electric
    0.08
    çļĦçĶµ
    0.08
    Activations Density 0.003%

    No Known Activations