© 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. 44503
    Prev
    Next
    INDEX
    Explanations

    string format placeholders

    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
    梯åŃIJ
    -0.07
    èĩªéĩį
    -0.06
    å°ģ
    -0.06
     signaling
    -0.06
    .SetActive
    -0.06
    genesis
    -0.06
     boycott
    -0.06
    ekut
    -0.06
    ancel
    -0.06
    ("/",
    -0.06
    POSITIVE LOGITS
    format
    0.10
    æł¼å¼ıåĮĸ
    0.10
    æł¼å¼ı
    0.10
    /format
    0.09
    formats
    0.09
     FORMAT
    0.09
     Formatter
    0.09
    =format
    0.09
    .Format
    0.09
     ÑĦоÑĢмаÑĤ
    0.09
    Activations Density 0.098%

    No Known Activations