© 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. 14950
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with exponentiation

    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
    cla
    -0.07
    upi
    -0.07
     Exit
    -0.07
    åĨķ
    -0.06
    å¤ı
    -0.06
    azzino
    -0.06
     exit
    -0.06
    AndGet
    -0.06
    ä¸Ģè¨Ģ
    -0.06
     inver
    -0.06
    POSITIVE LOGITS
    飬
    0.07
    天å¿ĥ
    0.07
    顺å¿ĥ
    0.07
    è¿ĻäºĽæķ°æį®
    0.07
    ç«ĭç§ĭ
    0.07
    人å¿ĥçļĦ
    0.07
    å¤Ħç½ļéĩij
    0.07
    èķĬ
    0.07
    å¾·åŁº
    0.07
    å¤ļå¤ļ
    0.07
    Activations Density 0.102%

    No Known Activations