© 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. 44674
    Prev
    Next
    INDEX
    Explanations

    compiler and linker errors

    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
    igmoid
    -0.07
     lawful
    -0.07
    Booking
    -0.07
    èĵĦ
    -0.07
     recharge
    -0.07
     sigmoid
    -0.07
    ¯
    -0.06
     govern
    -0.06
     Dawson
    -0.06
    ipple
    -0.06
    POSITIVE LOGITS
     compiler
    0.12
     compiling
    0.11
     compilation
    0.11
    Production
    0.11
     production
    0.11
    -production
    0.11
    compile
    0.11
    ç¼ĸè¯ij
    0.11
    .compile
    0.10
     Production
    0.10
    Activations Density 0.856%

    No Known Activations