© 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. 33487
    Prev
    Next
    INDEX
    Explanations

    style2

    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
    è¿IJè¾ĵ车è¾Ĩ
    -0.08
    ()):
    -0.07
    lev
    -0.06
    çIJ³å¨ľ
    -0.06
     ابت
    -0.06
    {text
    -0.06
    身åıĹ
    -0.06
    åįİé¾Ļ
    -0.06
    缸åħ³äº§åĵģ
    -0.06
    åİħéķ¿
    -0.06
    POSITIVE LOGITS
    çªŁ
    0.07
    (compare
    0.07
    PTY
    0.07
    西边
    0.07
     Ash
    0.07
    ä¸Ń西
    0.07
    éĢį
    0.06
    ITE
    0.06
    éĩĮ约
    0.06
    ittal
    0.06
    Activations Density 0.006%

    No Known Activations