© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46732
    Prev
    Next
    INDEX
    Explanations

    code context or programming constructs

    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
    Manifest
    -0.07
    upe
    -0.07
     Entw
    -0.07
    _RDWR
    -0.07
    åĽ½
    -0.07
    éĻIJãĤĬ
    -0.06
    à¸Īà¹īา
    -0.06
     invariably
    -0.06
     Blackhawks
    -0.06
    _BATCH
    -0.06
    POSITIVE LOGITS
    åı¯èĥ½ä¼ļæľī
    0.09
    èĭ¥æĥ³
    0.08
    asan
    0.08
     ols
    0.08
    åı¯èĥ½ä¼ļ
    0.08
    åı¯èĥ½ä¼ļ对
    0.07
    optional
    0.07
     optional
    0.07
    å¦ĤæŀľéľĢè¦ģ
    0.07
    ä¼ļå¼ķèµ·
    0.07
    Activations Density 0.003%

    No Known Activations