© 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. 4845
    Prev
    Next
    INDEX
    Explanations

    instructions or directions

    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
     therefore
    -0.10
    åĽłèĢĮ
    -0.10
     infatti
    -0.10
     thus
    -0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.09
    åħĪçľĭ
    -0.09
    åĽłæѤ
    -0.08
     ugyanis
    -0.08
    æѤæŶ
    -0.08
     totiž
    -0.08
    POSITIVE LOGITS
    éĹ®é¢ĺæĿ¥äºĨ
    0.10
    åĨįæİ¥
    0.10
     dilanjutkan
    0.09
    ä»Ĭ度ãģ¯
    0.09
    åħ¶ä»ĸçļĦ
    0.09
     altrettanto
    0.09
    åĨįéĢļè¿ĩ
    0.09
    就容æĺĵ
    0.09
     subsequent
    0.09
    åıĪä¼ļ
    0.09
    Activations Density 0.294%

    No Known Activations