© 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. 14183
    Prev
    Next
    INDEX
    Explanations

    creating new user or record

    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
     stead
    -0.07
    åĴ«å°º
    -0.07
    reden
    -0.07
    å²±
    -0.07
    /problems
    -0.07
    .getSelected
    -0.07
    aley
    -0.06
    å®ŀå¤Ħ
    -0.06
    -runtime
    -0.06
    å°½åľ¨
    -0.06
    POSITIVE LOGITS
     new
    0.12
    ä¸Ģ个æĸ°çļĦ
    0.11
    ä¸Ģ个æĸ°
    0.11
     новой
    0.10
     creation
    0.10
     mỼi
    0.10
     nuevos
    0.10
    æĸ°çļĦ
    0.10
    çļĦæĸ°
    0.10
     جدÙĬد
    0.10
    Activations Density 0.223%

    No Known Activations