© 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. 54938
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    楣
    -0.08
    大路
    -0.08
    iste
    -0.07
    inx
    -0.07
    anzi
    -0.06
    inq
    -0.06
    æī§è¡Įç¨ĭåºı
    -0.06
     Harapan
    -0.06
    othy
    -0.06
     Harmon
    -0.06
    POSITIVE LOGITS
    åľ°ä¹ħ
    0.08
    ziv
    0.08
    zik
    0.07
    为äºĨæĸ¹ä¾¿
    0.07
    سÙĬÙĦ
    0.06
    æijĩæ»ļ
    0.06
    urma
    0.06
    awy
    0.06
    à¸ģร
    0.06
    .intent
    0.06
    Activations Density 0.000%

    No Known Activations