© 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. 751
    Prev
    Next
    INDEX
    Explanations

    code block endings

    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
    lds
    -0.07
    ichter
    -0.07
     arm
    -0.07
     Prescott
    -0.07
    Arm
    -0.06
     Arm
    -0.06
    AVA
    -0.06
     Armstrong
    -0.06
    /play
    -0.06
    ops
    -0.06
    POSITIVE LOGITS
    åIJĮæŶ
    0.12
    åIJĮæĹ¶åľ¨
    0.12
    åIJĮæĹ¶å¯¹
    0.11
    ä¸İæѤåIJĮæŶ
    0.11
    åı¦ä¸Ģæĸ¹éĿ¢
    0.11
    åIJĮæĹ¶è¿Ľè¡Į
    0.10
    èĩ³äºİ
    0.10
     simultaneously
    0.10
    åIJĮæŶå°Ĩ
    0.10
     Meanwhile
    0.10
    Activations Density 0.160%

    No Known Activations