© 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. 61053
    Prev
    Next
    INDEX
    Explanations

    how to create

    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
    è¾ĥå¤ļçļĦ
    -0.06
    atten
    -0.06
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.06
    å¾Īå¥ĩæĢª
    -0.06
    çĿĢçļĦ
    -0.06
     birthdays
    -0.06
    ä¸Ńå°ı
    -0.05
    åĪ°æĿ¥
    -0.05
    äºĨçļĦ
    -0.05
     gotta
    -0.05
    POSITIVE LOGITS
    æĸ°çļĦ
    0.12
    /edit
    0.11
    ä¸Ģ个æĸ°çļĦ
    0.11
    /create
    0.10
    以èĩªå·±
    0.09
    åĴĮå®ŀæĸ½
    0.09
     new
    0.09
     daraus
    0.09
    å±ŀäºİèĩªå·±çļĦ
    0.09
    åĴĮ使çĶ¨
    0.09
    Activations Density 0.431%

    No Known Activations