© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55851
    Prev
    Next
    INDEX
    Explanations

    protocol buffer compiler code generation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åįķæĽ²
    -0.07
    riot
    -0.07
    èĨĽ
    -0.06
     táo
    -0.06
    åĿĬ
    -0.06
     Huck
    -0.06
    arrant
    -0.06
     Chor
    -0.06
    æ¡£
    -0.06
    _DM
    -0.06
    POSITIVE LOGITS
    _proto
    0.08
    /proto
    0.08
    protobuf
    0.08
     protobuf
    0.08
    codegen
    0.08
    åīĬ
    0.07
    lep
    0.07
    RPC
    0.07
     RPC
    0.07
    æ¶Īæģ¯
    0.07
    Activations Density 0.181%

    No Known Activations