© 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. 59768
    Prev
    Next
    INDEX
    Explanations

    "Received" date

    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
    åıĶ
    -0.07
    å°ıæľī
    -0.07
    èĻ
    -0.06
    é½¢
    -0.06
    ä¸Ģ线çļĦ
    -0.06
    ä¸īè¦ģ
    -0.06
    æ³ķãģ®
    -0.06
    _EXTRA
    -0.06
    åĪ©çļĦ
    -0.06
    æ³ķåĴĮ
    -0.06
    POSITIVE LOGITS
    æļĤæĹł
    0.10
     Various
    0.09
    Various
    0.09
    ä¸į详
    0.09
     various
    0.08
    æĹłéĹ»
    0.08
     Depends
    0.08
    none
    0.08
    depending
    0.08
    æĪijåIJĹ
    0.08
    Activations Density 0.543%

    No Known Activations