© 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. 27177
    Prev
    Next
    INDEX
    Explanations

    identify national

    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
    对åħ¶è¿Ľè¡Į
    -0.08
    åıijå±ķçļĦéľĢè¦ģ
    -0.08
    让è¿ĻäºĽ
    -0.08
    让è¿Ļ个
    -0.07
     thereof
    -0.07
     bersangkutan
    -0.07
     originals
    -0.07
     whichever
    -0.07
    åīįè¿°
    -0.07
    åĪĻ该
    -0.07
    POSITIVE LOGITS
    ierz
    0.09
    çļĵ
    0.08
    æ°ı
    0.07
    ÙĪغ
    0.07
    彤
    0.06
    :\/\/
    0.06
    ivin
    0.06
    ÙĦز
    0.06
    认è¯Ĩ
    0.06
     confr
    0.06
    Activations Density 0.027%

    No Known Activations