© 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. 568
    Prev
    Next
    INDEX
    Explanations

    -like or -style suffixes

    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
    kår
    -0.08
    inflam
    -0.07
    yment
    -0.07
    _operand
    -0.07
    udou
    -0.07
    MBER
    -0.07
     شرØŃ
    -0.07
    ách
    -0.07
    óf
    -0.07
    SSERT
    -0.07
    POSITIVE LOGITS
    -like
    0.28
    ähn
    0.19
    ä¼¼çļĦ
    0.19
    模æĭŁ
    0.17
    -style
    0.17
    -esque
    0.17
    like
    0.17
     mimic
    0.16
    подоб
    0.16
    èĪ¬çļĦ
    0.16
    Activations Density 0.703%

    No Known Activations