© 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. 21891
    Prev
    Next
    INDEX
    Explanations

    `_` delimited tokens

    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
    ancier
    -0.07
    ↵
    -0.06
    wy
    -0.06
    麻麻
    -0.06
    çıĬ
    -0.06
    dw
    -0.06
     `
    -0.05
    建åįİ
    -0.05
    �
    -0.05
    â
    -0.05
    POSITIVE LOGITS
    æľīæĿ¡ä»¶
    0.08
    )':
    0.08
    ä¹ĭçľ¼
    0.08
    ãģĿãģ®ä»ĸ
    0.08
    æİĴçļĦ
    0.08
    ä»Ĭ次
    0.08
     пÑĢоÑĩиÑħ
    0.08
    ookies
    0.08
    redits
    0.07
    åħ¶ä»ĸ
    0.07
    Activations Density 0.093%

    No Known Activations