© 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. 9223
    Prev
    Next
    INDEX
    Explanations

    in/among

    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
    м
    -0.10
    ä¸ŃåIJ«æľī
    -0.10
    ä¸Ńæľī
    -0.10
    åľ¨çİ©
    -0.10
    åľ¨åħ¶ä¸Ń
    -0.10
    ä¸ŃåĮħåIJ«
    -0.09
    ä¸Ń没æľī
    -0.09
    ä¸Ĭ没æľī
    -0.09
    åľ¨è¿Ļæł·çļĦ
    -0.09
    çļĦ缮åħī
    -0.09
    POSITIVE LOGITS
    ,
    0.08
    ï¼Į
    0.08
    ØĮ
    0.07
    çļĦä¸Ģ段æŶéĹ´
    0.07
    è¿Ľè¡ĮçļĦ
    0.07
    以åıĬåľ¨
    0.07
     lévÅij
    0.07
    çļĦ人们
    0.07
    çļĦ人æ°Ķ
    0.07
    çļĦ人åijĺ
    0.07
    Activations Density 0.004%

    No Known Activations