© 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. 25928
    Prev
    Next
    INDEX
    Explanations

    command signals instructions

    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
    èĩªè´¹
    -0.07
    窥
    -0.07
    Declared
    -0.07
    ä¹ĭçªĹ
    -0.07
    ssen
    -0.07
    -contrib
    -0.07
    ctime
    -0.07
    wab
    -0.06
    å¼ķåħ¥äºĨ
    -0.06
    åľ°åĪ©
    -0.06
    POSITIVE LOGITS
    æĮĩ令
    0.18
    æĮĩ示
    0.15
     instructions
    0.15
    ä¸ĭè¾¾
    0.14
    åij½ä»¤
    0.14
     commands
    0.14
     directives
    0.14
     directive
    0.14
     instruct
    0.13
    สัà¹Īà¸ĩ
    0.13
    Activations Density 0.398%

    No Known Activations