© 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. 2569
    Prev
    Next
    INDEX
    Explanations

    World War II captivity camps

    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
     Islamabad
    -0.08
     IPL
    -0.08
    chetta
    -0.08
     senaste
    -0.08
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.08
    è¸ıéĿĴ
    -0.07
     desirable
    -0.07
    recent
    -0.07
    æĸ°ä¸Ģå±Ĭ
    -0.07
    å½ĵåīįçļĦ
    -0.07
    POSITIVE LOGITS
     during
    0.10
    å½ĵæŶ
    0.08
    during
    0.08
     During
    0.08
     durante
    0.08
    During
    0.07
    åIJİæľŁ
    0.07
     POW
    0.07
     documented
    0.07
    oose
    0.07
    Activations Density 0.548%

    No Known Activations