© 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. 48306
    Prev
    Next
    INDEX
    Explanations

    current motion

    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
     Singer
    -0.07
     \"
    -0.07
    ewel
    -0.07
    inker
    -0.07
    pec
    -0.07
    aglia
    -0.07
    æĶĴ
    -0.07
    å¥Ķèµ°
    -0.07
    鸾
    -0.07
    çļĦå¤ĸéĥ¨
    -0.07
    POSITIVE LOGITS
    éĩij森
    0.08
    å²IJ
    0.08
    è°IJéŁ³
    0.08
    大è¯Ŀ
    0.07
    æĿ¥åºĹ
    0.07
    大浪
    0.07
    ertime
    0.07
     hilar
    0.07
    ä¸Ģé¡Ĩ
    0.07
     tweeting
    0.07
    Activations Density 0.639%

    No Known Activations