© 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. 56349
    Prev
    Next
    INDEX
    Explanations

    "context" followed by punctuation

    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
    èĢĮéĻį
    -0.08
    ä¹ĭåŁİ
    -0.08
    é¦ĸåħĪæĺ¯
    -0.08
    è¿Ľè¡ĮåŃ¦ä¹ł
    -0.08
    lafen
    -0.07
    好æĥ³
    -0.07
    ä½łä»¬éĥ½
    -0.07
    ebes
    -0.07
    æĮīçħ§è§Ħå®ļ
    -0.07
     Firstly
    -0.07
    POSITIVE LOGITS
    çļĦè¿Ļä¸Ģ
    0.12
    çļĦè¿Ļç§į
    0.12
    对è¿ĻäºĽ
    0.11
     this
    0.11
    对æѤ
    0.11
    this
    0.10
     ìĿ´ëŁ¬íķľ
    0.10
    è¿Ļç§į
    0.10
    çļĦè¿ĻäºĽ
    0.10
     ÙĦÙĩØ°Ùĩ
    0.10
    Activations Density 0.470%

    No Known Activations