© 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. 23485
    Prev
    Next
    INDEX
    Explanations

    Chinese characters, punctuation, and code concepts

    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
    phem
    -0.08
    serter
    -0.08
    精彩åĨħ容
    -0.07
    nav
    -0.07
    ettel
    -0.07
    zyw
    -0.07
    ennen
    -0.07
    eties
    -0.07
    æĺĵè´Ń
    -0.07
    libc
    -0.07
    POSITIVE LOGITS
    æŁIJ
    0.11
    æŁIJ人
    0.11
    æŁIJç§į
    0.11
    æĬĬäºĭæĥħ
    0.11
    æŁIJ个
    0.10
    åľ¨æŁIJ
    0.10
    æŁIJæŁIJ
    0.10
    æŁIJä¸Ģ
    0.09
    åģļäºĭæĥħ
    0.09
    ä¸Ģ件äºĭæĥħ
    0.08
    Activations Density 0.138%

    No Known Activations