© 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. 16057
    Prev
    Next
    INDEX
    Explanations

    phenomena and specific medical/technical terms

    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
     Zad
    -0.08
    ammans
    -0.08
    hab
    -0.08
    æĴ®
    -0.07
    æ±°
    -0.07
    人åĿĩåı¯
    -0.07
    宾
    -0.07
    çĴŀ
    -0.07
    iliz
    -0.07
    <?,
    -0.07
    POSITIVE LOGITS
     phenomenon
    0.09
    çݰ象
    0.08
    çŃīçݰ象
    0.08
    主è¦ģæĺ¯çĶ±äºİ
    0.07
     phenomena
    0.07
    å°±æĺ¯åĽłä¸º
    0.07
    尽管å¦ĤæѤ
    0.07
    çļĦåİŁåĽłä¹ĭä¸Ģ
    0.07
    isl
    0.06
    çļĦçݰ象
    0.06
    Activations Density 0.019%

    No Known Activations