© 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. 50461
    Prev
    Next
    INDEX
    Explanations

    Teens For or Lenovo Net

    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
    è¹ĭ
    -0.08
    ãģ¾ãģı
    -0.07
     neut
    -0.07
    åĿıäºĭ
    -0.07
    å°ı说ç½ij
    -0.06
     prin
    -0.06
    anga
    -0.06
    çĶŁæķĪ
    -0.06
     staple
    -0.06
    è¿IJ
    -0.06
    POSITIVE LOGITS
    ingan
    0.07
    çļĦä¸Ģéģĵ
    0.07
    OLON
    0.07
    OLVE
    0.07
    é¬
    0.07
    ائÛĮ
    0.07
    leger
    0.07
    å¦ĤæŀľæĤ¨
    0.07
    çľģçļĦ
    0.07
     SCR
    0.07
    Activations Density 0.001%

    No Known Activations