© 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. 9129
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    ÙĴرÙIJ
    -0.07
    JET
    -0.06
    agio
    -0.06
    èµ·å±ħ
    -0.06
    IANA
    -0.06
    åħ¶æīĢ
    -0.06
    waan
    -0.06
    æ¡ĶåŃIJ
    -0.06
    æļĹæļĹ
    -0.06
    пло
    -0.06
    POSITIVE LOGITS
    è¿Ļå¥Ĺ
    0.08
    arnos
    0.07
    é£ŀé¾Ļ
    0.07
    å¤įæĿĤçļĦ
    0.07
    以ä¸Ĭå°±æĺ¯
    0.07
    arna
    0.06
    æľ¬ç«ĻæīĢæľī
    0.06
    į
    0.06
    amil
    0.06
    uhkan
    0.06
    Activations Density 0.153%

    No Known Activations