© 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. 9547
    Prev
    Next
    INDEX
    Explanations

    mechanical and electrical components

    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
    ä¸ĢæŶ
    -0.06
    eki
    -0.06
    /all
    -0.06
    èģĮä¸ļåѦéĻ¢
    -0.06
    اÙĨÙĩ
    -0.06
    hi
    -0.06
    iw
    -0.06
    ÃŃc
    -0.06
    æĸĩ
    -0.06
    ylie
    -0.06
    POSITIVE LOGITS
    æīĢåľ¨çļĦä½įç½®
    0.10
    æīĢåľ¨ä½įç½®
    0.09
    æīĢåľ¨çļĦ
    0.09
    æī¼
    0.09
    æīĢå¤ĦçļĦ
    0.09
    æīĢå¤Ħ
    0.08
    æīĢåľ¨
    0.08
    ãģ¨ãģĿãģ®
    0.08
    èĥĮéĿł
    0.08
     placement
    0.08
    Activations Density 0.293%

    No Known Activations