© 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. 12613
    Prev
    Next
    INDEX
    Explanations

    terminal domains and regions

    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
    atte
    -0.07
     Nation
    -0.07
    ä»°
    -0.07
    åŃĺéĩı
    -0.07
    á»Ŀ
    -0.06
    usche
    -0.06
     ë¹
    -0.06
     пок
    -0.06
     Pon
    -0.06
    å®ļçĦ¶
    -0.06
    POSITIVE LOGITS
    段çļĦ
    0.11
    段
    0.11
    åħ¨éķ¿
    0.11
     portions
    0.10
     portion
    0.10
    è¿Ļ段
    0.10
     segments
    0.09
    ä¸Ģ段
    0.09
    ä¸Ń段
    0.09
    两段
    0.09
    Activations Density 0.321%

    No Known Activations