© 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. 42364
    Prev
    Next
    INDEX
    Explanations

    any kind of queries

    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
    æĿİæĻĵ
    -0.07
    antau
    -0.07
    è¾ĥå¥½åľ°
    -0.07
    èIJ½äºĨ
    -0.07
    NR
    -0.06
    å¾Ģäºĭ
    -0.06
    å¨ľå¨ľ
    -0.06
    TRO
    -0.06
    åĪ°æĻļ
    -0.06
    Ľ°
    -0.06
    POSITIVE LOGITS
     diverse
    0.09
    èĮĥåĽ´å¹¿
    0.08
    ä»»æĦı
    0.08
     arbitrary
    0.07
    对æīĢæľī
    0.07
    å¤ļæł·åĮĸçļĦ
    0.07
     supposedly
    0.07
    èĮĥåĽ´
    0.07
    èĮĥåĽ´åĴĮ
    0.07
    åIJİ天
    0.07
    Activations Density 0.016%

    No Known Activations