© 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. 18013
    Prev
    Next
    INDEX
    Explanations

    electromagnetism and charge

    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
    并èĮĤ
    -0.08
    è¿ijå¹³
    -0.07
    容积
    -0.07
    papan
    -0.07
    úl
    -0.07
    Ñģпен
    -0.07
    çļĦéĿĴæĺ¥
    -0.07
    éĢłåĮĸ
    -0.07
    壯
    -0.07
    mtime
    -0.07
    POSITIVE LOGITS
     neutrality
    0.08
    ä¸ŃæĢ§
    0.08
     اÙĦÙĥÙĩربائÙĬØ©
    0.08
     neutral
    0.07
    ä¸ĩåĽ½
    0.07
    导ä½ĵ
    0.07
     conduct
    0.07
     Conduct
    0.07
     electromagnetic
    0.07
     conductor
    0.07
    Activations Density 0.003%

    No Known Activations