© 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. 52113
    Prev
    Next
    INDEX
    Explanations

    code

    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
    .googleapis
    -0.06
     DXGI
    -0.06
     Military
    -0.06
     muted
    -0.06
     arbit
    -0.06
    .sock
    -0.06
    æij¸æ¸ħ
    -0.06
     Cush
    -0.06
    æĢ»æ¯Ķ
    -0.06
    .appspot
    -0.06
    POSITIVE LOGITS
    代çłģ
    0.17
     code
    0.16
     código
    0.14
    -code
    0.13
    code
    0.13
     codice
    0.13
    çļĦ代çłģ
    0.13
     код
    0.13
    ãĤ³ãĥ¼ãĥī
    0.12
    _code
    0.12
    Activations Density 1.744%

    No Known Activations