© 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. 30845
    Prev
    Next
    INDEX
    Explanations

    user interface usability

    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
    åĿļ硬
    -0.07
    楼ä¸Ĭ
    -0.07
    æķ°æį®åºĵä¸Ń
    -0.07
    çĽ¸å¯¹ç¨³å®ļ
    -0.07
    ä¸įéĢı
    -0.07
    ä»ĸ身ä¸Ĭ
    -0.07
    åºķæ°Ķ
    -0.06
    ØŃض
    -0.06
    声ä¸Ń
    -0.06
    æľīæĿ¡ä»¶
    -0.06
    POSITIVE LOGITS
    æĺĵçĶ¨
    0.14
     interface
    0.12
    çķĮéĿ¢
    0.12
     user
    0.12
     interfaces
    0.12
    让çĶ¨æĪ·
    0.11
     UX
    0.11
    çĶ¨æĪ·ä½ĵéªĮ
    0.11
    User
    0.11
    çļĦçĶ¨æĪ·
    0.11
    Activations Density 0.297%

    No Known Activations