© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29310
    Prev
    Next
    INDEX
    Explanations

    election, champion, title, year

    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
    BeforeEach
    -0.07
     inf
    -0.07
    嵩
    -0.06
    å§ijèĭı
    -0.06
    éļIJ
    -0.06
     sed
    -0.06
    çĤĴ
    -0.06
    charAt
    -0.06
    åļı
    -0.06
    он
    -0.06
    POSITIVE LOGITS
    å°±åľ¨è¿Ļ
    0.08
    æŃ£å¼ıæĪIJç«ĭ
    0.07
    éĩijåħī
    0.07
    ampoo
    0.07
    agrant
    0.07
    zio
    0.07
    æ±Ĥå¾Ĺ
    0.07
    änden
    0.07
    neau
    0.07
    rint
    0.07
    Activations Density 0.022%

    No Known Activations