© 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. 47413
    Prev
    Next
    INDEX
    Explanations

    will be described

    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
    èIJ½äºĨ
    -0.07
    вален
    -0.07
    æĺ¥æļĸ
    -0.07
    thic
    -0.07
    äºĨè¿Ľåİ»
    -0.07
    è¡Įäºij
    -0.07
     colum
    -0.06
    sure
    -0.06
    urgo
    -0.06
    çŃīå¾ħçĿĢ
    -0.06
    POSITIVE LOGITS
     briefly
    0.08
    å±ķå¼Ģåħ¨éĥ¨
    0.07
    adem
    0.07
    åĪĨæŀIJæĸ¹æ³ķ
    0.07
    /disc
    0.07
    两ç§įæĸ¹å¼ı
    0.07
    nou
    0.07
    åĻ¨åĴĮ
    0.07
    æĺİå¾·
    0.07
    brief
    0.07
    Activations Density 0.162%

    No Known Activations