© 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. 4050
    Prev
    Next
    INDEX
    Explanations

    event timing

    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
    åĴĨ
    -0.08
     eup
    -0.07
     Boeh
    -0.07
    γÏī
    -0.07
    è¿Ļ个æķ°åŃĹ
    -0.07
    æĸ¹åIJij
    -0.07
    å¾ĢæľŁåĽŀ顾
    -0.07
     ë°©íĸ¥ìľ¼ë¡ľ
    -0.07
     gimm
    -0.07
     bid
    -0.07
    POSITIVE LOGITS
     events
    0.10
    åıijçĶŁåľ¨
    0.10
    åıijçĶŁäºİ
    0.09
     coordinates
    0.09
     timestamps
    0.09
    åľ°çĤ¹
    0.09
    åıijçĶŁæŶ
    0.09
     timing
    0.09
    äºĭ件çļĦ
    0.09
     ÑģобÑĭÑĤиÑı
    0.09
    Activations Density 0.002%

    No Known Activations