© 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. 2184
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming keywords

    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
    nga
    -0.06
    ä¸ĭéĿ¢
    -0.06
    оÑĤо
    -0.06
    as
    -0.06
    åĽŀ羸
    -0.06
    xiv
    -0.06
    man
    -0.06
    ush
    -0.06
    eng
    -0.06
    âĨIJ
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.10
    )':
    0.09
     обаÑĩе
    0.09
    )":
    0.09
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.08
    åĬ¨åĬĽæĸ¹éĿ¢
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    俱ä¹IJéĥ¨
    0.08
    æŁ¥çľĭæĽ´å¤ļ
    0.08
    éħįç½®æĸ¹éĿ¢
    0.08
    Activations Density 0.050%

    No Known Activations