© 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. 9007
    Prev
    Next
    INDEX
    Explanations

    the world

    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
    è°ģ家
    -0.07
    æĹłéĹ»
    -0.07
    å¯¹åľ¨
    -0.07
     stranded
    -0.07
    evin
    -0.07
    iform
    -0.07
    ä¸ī代
    -0.06
    ytu
    -0.06
    èħ°
    -0.06
    stp
    -0.06
    POSITIVE LOGITS
    ä¸ĩ象
    0.10
    山河
    0.09
    iverse
    0.09
    å±ķçİ°åľ¨
    0.08
    -wide
    0.08
     ÙĪاÙĦعاÙĦÙħ
    0.08
    æīijéĿ¢
    0.08
    大ä¸ĸçķĮ
    0.08
    æĻ¯èī²
    0.08
    åijĪçİ°åľ¨
    0.07
    Activations Density 0.101%

    No Known Activations