© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52037
    Prev
    Next
    INDEX
    Explanations

    Foundation

    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
    Negative Logits
    ahoo
    -0.09
    à¥įस
    -0.09
    ugno
    -0.09
    phans
    -0.09
    ients
    -0.09
    .sharedInstance
    -0.09
    soever
    -0.08
    ãĤĪãģĨãģ«
    -0.08
    æĥķ
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    POSITIVE LOGITS
    ìłģìĿ¸
    0.09
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    æĢ§çļĦ
    0.07
    ãģĺãĤģãģ¦
    0.07
    zed
    0.07
    æĢ§åĴĮ
    0.07
    ç§ijåѦçłĶ究éĻ¢
    0.06
    æĢ§åľ°
    0.06
    ей
    0.06
    enticated
    0.06
    Activations Density 0.017%

    No Known Activations