© 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. 9710
    Prev
    Next
    INDEX
    Explanations

    phosphatase

    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
    æīĢ欲
    -0.10
    æħµ
    -0.09
    æīĢå¤Ħ
    -0.08
    комо
    -0.08
    æīĢå¤ĦçļĦ
    -0.08
    ä¸Ģå¸Ĩ
    -0.08
    æīĢæľª
    -0.08
    缴æİ¥æĪĸ
    -0.08
    .nasa
    -0.08
    迪士
    -0.08
    POSITIVE LOGITS
    èįļ
    0.06
    ç¥ł
    0.06
    vs
    0.06
    arbonate
    0.05
    æķĻèĤ²åѦéĻ¢
    0.05
    /
    0.05
     пÑĢоÑĪло
    0.05
    åĮºéķ¿
    0.05
    पाल
    0.05
     Äijạo
    0.05
    Activations Density 0.429%

    No Known Activations