© 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. 18059
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ´»åĬ¨åľ¨
    -0.08
    å°½æľī
    -0.08
    ä¸įæıIJ
    -0.07
    æ´»åĬ¨åĴĮ
    -0.07
    åĩºéŨ
    -0.07
    ilot
    -0.07
     reasons
    -0.07
    коло
    -0.07
    åĿı
    -0.07
     Reasons
    -0.07
    POSITIVE LOGITS
    incon
    0.07
    å°±æĺ¯è¦ģ
    0.07
    angan
    0.07
    é½
    0.07
    عÙĬÙĨ
    0.07
    ense
    0.06
    inery
    0.06
    uck
    0.06
     intitul
    0.06
    asa
    0.06
    Activations Density 0.000%

    No Known Activations