© 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. 4816
    Prev
    Next
    INDEX
    Explanations

    quantifiable attributes

    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
    æµĵ度为
    -0.08
    æķ°éĩı为
    -0.08
    妩
    -0.08
    åĭĭ
    -0.08
    温度为
    -0.08
    zan
    -0.07
    ÙĨز
    -0.07
    é¢Ŀ为
    -0.07
    -kind
    -0.07
    çĭ©
    -0.07
    POSITIVE LOGITS
    åĨ³å®ļäºĨ
    0.09
    è¶Ĭ大
    0.09
    åĨ³å®ļçļĦ
    0.08
    è¶ĬæĹ©
    0.08
    è¶Ĭéķ¿
    0.08
    è¶Ĭé«ĺ
    0.08
    è¶Ĭå°ı
    0.07
     décro
    0.07
     determines
    0.07
    è¶Ĭä½İ
    0.07
    Activations Density 0.092%

    No Known Activations