© 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. 54924
    Prev
    Next
    INDEX
    Explanations

    whether, yes

    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
    gris
    -0.08
     <![
    -0.08
    illon
    -0.08
    resher
    -0.08
    orage
    -0.08
    CardContent
    -0.08
    -uri
    -0.08
    ä¹ĭ书
    -0.08
    erea
    -0.08
    riff
    -0.08
    POSITIVE LOGITS
    åIJ¦
    0.09
    羣çļĦæľī
    0.08
    æĺ¯åIJ¦
    0.08
    æŀľçľŁ
    0.08
     ìŬë¶Ģ
    0.08
     whether
    0.08
    æĺ¯åIJ¦åħ·æľī
    0.07
    æĬijæĪĸ
    0.07
    _yes
    0.07
     yes
    0.07
    Activations Density 0.202%

    No Known Activations