© 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. 48178
    Prev
    Next
    INDEX
    Explanations

    variable division or equations

    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
    witz
    -0.08
    éĵ®
    -0.07
    furter
    -0.07
    åħµçİĭ
    -0.07
    biz
    -0.07
    ption
    -0.07
    _concat
    -0.07
    å¿«
    -0.07
    æ¸Ŀ
    -0.07
     plato
    -0.07
    POSITIVE LOGITS
    éné
    0.08
    óle
    0.06
    uto
    0.06
    ika
    0.06
     Serif
    0.06
    ência
    0.06
    Ĭ
    0.06
    åıĮåıĮ
    0.06
    åĩĨç¡®åľ°
    0.06
    è¿Ļ个ä¸ĸçķĮä¸Ĭ
    0.06
    Activations Density 0.115%

    No Known Activations