© 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. 62463
    Prev
    Next
    INDEX
    Explanations

    Chinese and technical terms

    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
     Completely
    -0.07
     hinweg
    -0.07
    éĥ½ä¸į好
    -0.07
    è¿Ļ两款
    -0.07
    åĬ¨æĦŁ
    -0.07
    aisy
    -0.07
    太éļ¾
    -0.06
    å¼ķèµ·äºĨ
    -0.06
    åıĪæĿ¥äºĨ
    -0.06
    ¿
    -0.06
    POSITIVE LOGITS
    æѤæŶçļĦ
    0.08
     coincide
    0.08
     unchanged
    0.08
    å®ļæł¼
    0.08
    å¯ħ
    0.08
    è¿ĻæŶçļĦ
    0.07
    èĴ¸èĴ¸
    0.07
    èIJ½åľ¨
    0.07
    æľ¬äººèº«ä»½è¯ģ
    0.07
     nomin
    0.07
    Activations Density 0.036%

    No Known Activations