© 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. 581
    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
    éĹ»
    -0.07
    aper
    -0.06
    shr
    -0.06
    olls
    -0.06
    arf
    -0.06
     heterogeneous
    -0.06
    oft
    -0.06
    /
    -0.06
    al
    -0.06
    æĭĶ
    -0.06
    POSITIVE LOGITS
    ynu
    0.08
     scat
    0.08
    -badge
    0.08
    æīĭæı¡
    0.08
    üh
    0.08
    =root
    0.08
    رÙĪÙĤ
    0.08
    æīĵè¿ĩ
    0.08
    æī§è¡Įèij£äºĭ
    0.08
    PathComponent
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.