© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61946
    Prev
    Next
    INDEX
    Explanations

    value or some_value

    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
    å¦ĤæĤ¨
    -0.07
    没æľīåľ¨
    -0.07
    èļĬèĻ«
    -0.06
    _hdl
    -0.06
    å°Ĩæķ´ä¸ª
    -0.06
     HttpHeaders
    -0.06
    æ¡ĤåĨł
    -0.06
     inilah
    -0.06
    _sur
    -0.06
    _intr
    -0.06
    POSITIVE LOGITS
    æŁIJä¸Ģ天
    0.09
     certain
    0.08
    åľ¨æŁIJ
    0.08
    виÑĨа
    0.08
    ä¹ĭç±»çļĦ
    0.07
    IsActive
    0.07
    æŁIJ
    0.07
     ÙħعÙĬÙĨØ©
    0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    0.07
    ertain
    0.07
    Activations Density 0.017%

    No Known Activations