© 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. 59832
    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
    ught
    -0.08
    emis
    -0.07
     hebt
    -0.07
    çijŁ
    -0.07
    ROWS
    -0.07
    inate
    -0.06
    鸳
    -0.06
    ién
    -0.06
    å¾Ĵæīĭ
    -0.06
     handy
    -0.06
    POSITIVE LOGITS
    Äįi
    0.08
    ä¸įæĺ¯è¯´
    0.07
    æīį好
    0.07
    Bud
    0.07
    çī¹å°Ķ
    0.07
    riz
    0.07
    ench
    0.07
    æĪĸå°ij
    0.07
    uiu
    0.07
     Boulevard
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.