© 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. 3456
    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
    ctl
    -0.07
    æīįèĥ½å¾ĹåĪ°
    -0.07
    表示äºĨ
    -0.07
    umba
    -0.07
    OTH
    -0.07
    åħģ
    -0.07
    容纳
    -0.07
    continued
    -0.07
    ota
    -0.06
    表æĺİ
    -0.06
    POSITIVE LOGITS
     ril
    0.07
    羯
    0.07
     refr
    0.07
    iren
    0.06
    iming
    0.06
    olec
    0.06
    èĦ¸
    0.06
    åĩºçĶŁåľ¨
    0.06
    ä¹ĭè¾Ī
    0.06
    çļĦ设计åĴĮ
    0.06
    Activations Density 0.000%

    No Known Activations