© 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. 6944
    Prev
    Next
    INDEX
    Explanations

    structural nested models

    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
    agraph
    -0.07
    æ³¥
    -0.07
    è¿Ļä¸ľè¥¿
    -0.07
    åĩ½
    -0.07
    纵横
    -0.06
    èħ¹
    -0.06
     cases
    -0.06
    бий
    -0.06
    Spl
    -0.06
    åĨł
    -0.06
    POSITIVE LOGITS
    -agent
    0.08
    çĻ¾å²ģ
    0.07
    earn
    0.07
    æĦ
    0.07
    çľĭåIJij
    0.07
     Gover
    0.07
    olica
    0.07
     secu
    0.07
    ayers
    0.07
     Roths
    0.07
    Activations Density 0.002%

    No Known Activations