© 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. 8600
    Prev
    Next
    INDEX
    Explanations

    first, second, part, former

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
    æŁIJ天
    -0.07
    /css
    -0.06
    ç½ķ
    -0.06
    ä¸Ģ声
    -0.06
     aliqua
    -0.06
    çļĦæľĢé«ĺ
    -0.06
    æŁIJä¸Ģ天
    -0.06
    å®ĩ
    -0.06
    èĤļ
    -0.06
    POSITIVE LOGITS
    éħįç½®æĸ¹éĿ¢
    0.08
    æĹ¢çĦ¶æĺ¯
    0.08
    åĬ¨åĬĽæĸ¹éĿ¢
    0.07
    ols
    0.07
    éĢĻéĤĬ
    0.07
    åºĶä»İ
    0.07
    说åĪ°
    0.07
     dataArray
    0.07
    åĪĻä¼ļ
    0.07
    éĤ£éĤĬ
    0.07
    Activations Density 0.009%

    No Known Activations