© 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. 4670
    Prev
    Next
    INDEX
    Explanations

    managing and planning tasks

    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
    åıĪ被
    -0.08
    urable
    -0.08
    æĢ»åĮ»éĻ¢
    -0.07
    æŶ任
    -0.07
    ysin
    -0.07
    å¹³åĿĩæ°´å¹³
    -0.07
    åĪ©ç©º
    -0.07
     Murdoch
    -0.07
    é£Ĵ
    -0.07
    å·¥ä½ľå®ŀéĻħ
    -0.07
    POSITIVE LOGITS
    并ç»Ħç»ĩ
    0.10
     lia
    0.10
    并确ä¿Ŀ
    0.10
    åįıè°ĥ
    0.09
     Lia
    0.09
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.09
     oversees
    0.09
     oversee
    0.09
    交åĬŀçļĦåħ¶ä»ĸ
    0.08
     behalf
    0.08
    Activations Density 0.188%

    No Known Activations