© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52098
    Prev
    Next
    INDEX
    Explanations

    stock, trading, financial transactions

    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
    Negative Logits
    汽车工ä¸ļ
    -0.07
    æĸ½å·¥è¿Ľåº¦
    -0.07
    antry
    -0.06
    ä¸įåĪ°äºĨ
    -0.06
    عب
    -0.06
    é¾Ħ
    -0.06
    æİ¢ç§ĺ
    -0.06
    identa
    -0.06
    è¿ĩåĨ¬
    -0.06
    angler
    -0.06
    POSITIVE LOGITS
    波段
    0.10
    매
    0.08
    åįĸåĩº
    0.08
    -buy
    0.08
    zos
    0.07
    æıIJ
    0.07
    ä¹°åħ¥
    0.07
     매
    0.07
    éĭĴ
    0.07
    æĥłåĨľ
    0.07
    Activations Density 0.002%

    No Known Activations