© 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. 44428
    Prev
    Next
    INDEX
    Explanations

    contents of files and parcels

    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
    ä¸Ĭå¹´åIJĮæľŁ
    -0.08
    ä»ĭ
    -0.07
    ä¸Ń央社
    -0.07
    碳达峰
    -0.07
    بت
    -0.07
    éķ¿çº¿
    -0.07
     $('#'
    -0.06
    ä¸Ģä¾ĭ
    -0.06
    ä¸ĢåĬ¨
    -0.06
    åľĨåľĨçļĦ
    -0.06
    POSITIVE LOGITS
     explicitly
    0.11
    éĻĦ
    0.10
    Explicit
    0.10
    explicit
    0.10
    éĻĦ带
    0.10
    éĻĦæľī
    0.10
    èĩªå¸¦
    0.09
     Explicit
    0.09
    æĺİç¡®è¦ģæ±Ĥ
    0.09
    æłĩæĺİ
    0.09
    Activations Density 0.790%

    No Known Activations