© 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. 26476
    Prev
    Next
    INDEX
    Explanations

    Chinese text preceding English words or code

    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
    rade
    -0.08
    åij¼åĴĮ
    -0.07
     dén
    -0.07
    èĮĥæĸĩç½ij
    -0.07
    åı¯ä»¥åĨį
    -0.06
    ึ
    -0.06
    粪
    -0.06
    Raised
    -0.06
    èĮģ壮
    -0.06
    esel
    -0.06
    POSITIVE LOGITS
    ä½įæķ°
    0.08
    zut
    0.07
    æħ
    0.07
    utin
    0.07
    ctal
    0.07
    è¿Ļ个æĹ¶ä»£
    0.07
    arden
    0.07
    factor
    0.07
    çĴŀ
    0.07
     sconos
    0.07
    Activations Density 0.157%

    No Known Activations