© 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. 25831
    Prev
    Next
    INDEX
    Explanations

    leptonic b, c, tau decays

    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
    iaux
    -0.07
    é²ľ
    -0.07
    è·¤
    -0.06
     voisin
    -0.06
    çļĦçĬ¶æĢģ
    -0.06
    æİĴ头
    -0.06
    éĤ»
    -0.06
    çļ®çļĦ
    -0.06
     undertaking
    -0.06
    ä½Ļ
    -0.06
    POSITIVE LOGITS
     Ðŀбо
    0.08
     Ø¥ÙĬ
    0.08
    _ATTR
    0.08
    .writer
    0.07
    äºĮæī¹
    0.07
    mira
    0.07
     Trident
    0.07
    两æĶ¯
    0.07
    ино
    0.07
    полÑı
    0.07
    Activations Density 0.004%

    No Known Activations