© 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. 26935
    Prev
    Next
    INDEX
    Explanations

    prediction and negative outcomes

    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¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    -0.07
    landing
    -0.07
    č↵
    -0.06
    åı½
    -0.06
    ãģ¨ãģ®ãģĵãģ¨
    -0.06
    以ä¸ĭç®Ģ称
    -0.06
    æīĢåij¨
    -0.06
    าà¸Ļัà¹īà¸Ļ
    -0.06
    以ä¸ĭæĺ¯å°ıç¼ĸ
    -0.06
    çIJ¥
    -0.06
    POSITIVE LOGITS
    çļĦè¿ĻäºĽ
    0.10
    æĬĬè¿ĻäºĽ
    0.10
    æīĢæľīè¿ĻäºĽ
    0.09
    èĩ³æѤ
    0.09
    éĢļè¿ĩ以ä¸Ĭ
    0.09
    å°±è¿Ļæł·
    0.09
    åľ¨è¿ĻäºĽ
    0.09
    å°Ĩè¿ĻäºĽ
    0.08
     tehát
    0.08
    èĢĮè¿ĻäºĽ
    0.08
    Activations Density 0.384%

    No Known Activations