© 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. 10079
    Prev
    Next
    INDEX
    Explanations

    template

    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
    å¨ĵ
    -0.07
    -opacity
    -0.07
    æ±ĩ
    -0.07
    MainThread
    -0.07
    ä¹ĸ
    -0.06
    ehren
    -0.06
    åĪ°å¤©
    -0.06
    ç³»ç»Łå·¥ç¨ĭ
    -0.06
    agged
    -0.06
    çļĦéĩįè¦ģæīĭ段
    -0.06
    POSITIVE LOGITS
    模æĿ¿
    0.20
     templates
    0.19
     template
    0.18
    /template
    0.18
    模çīĪ
    0.18
    templates
    0.17
    template
    0.16
     Templates
    0.16
    -template
    0.15
    /templates
    0.15
    Activations Density 0.394%

    No Known Activations