© 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. 48754
    Prev
    Next
    INDEX
    Explanations

    military and defensive capabilities

    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
    à¹īà¸Ńà¸Ļ
    -0.08
    帮åĬ©åĪ«äºº
    -0.08
    é¢Ŀ为
    -0.07
    δαÏĤ
    -0.07
    /Library
    -0.07
    clare
    -0.07
    trä
    -0.07
    æĭ¯æķij
    -0.07
    æŃ´
    -0.07
    ETCH
    -0.07
    POSITIVE LOGITS
    æ¯ĶæĪij们
    0.10
    æ¯Ķä½ł
    0.10
    è¶ģ
    0.09
    对æĪij们çļĦ
    0.09
    伺
    0.09
    å¨ģèĥģ
    0.09
    è½»æĺĵ
    0.09
     threatens
    0.08
     threaten
    0.08
    ä¼ģåĽ¾
    0.08
    Activations Density 0.299%

    No Known Activations