© 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. 34959
    Prev
    Next
    INDEX
    Explanations

    parentheses or comma followed by numbers

    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
    åı³ä¸ĭ
    -0.07
    åı¦å¤ĸä¸Ģ个
    -0.07
    åIJijåı³
    -0.07
     afford
    -0.07
    éĢĨæµģ
    -0.07
    ä»İå°ı
    -0.06
    åı¦ä¸Ģ
    -0.06
     tenure
    -0.06
     affiliate
    -0.06
    ä¸īäºĶ
    -0.06
    POSITIVE LOGITS
    åıĮåıĮ
    0.10
     sym
    0.10
     Sym
    0.10
    对称
    0.09
    Sym
    0.09
     symmetric
    0.09
    _sym
    0.08
    ä¸ŃéĹ´çļĦ
    0.08
    sym
    0.08
     widest
    0.08
    Activations Density 0.037%

    No Known Activations