© 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. 24382
    Prev
    Next
    INDEX
    Explanations

    asking for

    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
    精彩åĨħ容
    -0.08
    åĴĮ幸ç¦ı
    -0.07
    atomy
    -0.07
     Schau
    -0.07
    åıĸå¾ĹçļĦæĪIJ绩
    -0.07
    AndGet
    -0.07
    æľ¬æĸĩ为
    -0.07
    书åIJ§
    -0.07
    assi
    -0.07
    å¾Ĺåĩºç»ĵ论
    -0.07
    POSITIVE LOGITS
     clarification
    0.08
    çļĦæĺ¯ä¸Ģ个
    0.08
     answers
    0.07
    ä¸Ģ个æĸ°çļĦ
    0.07
    ined
    0.07
    çļĦçŃĶæ¡Ī
    0.07
    çļĦä¸įæĺ¯
    0.07
     assurances
    0.07
    ä¸Ģ个大
    0.07
    ä¸Ģå¥Ĺ
    0.07
    Activations Density 0.038%

    No Known Activations