© 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. 32937
    Prev
    Next
    INDEX
    Explanations

    ãĢĤ. An, Erik, Proceedings

    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
    ë¡ľ
    -0.07
    <|repo_name|>
    -0.07
    Margin
    -0.07
    acl
    -0.06
    akov
    -0.06
    æ²
    -0.06
    usak
    -0.06
    çļĦ
    -0.06
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.06
     domic
    -0.06
    POSITIVE LOGITS
    主è¦ģ以
    0.08
    管çIJĨæĸ¹éĿ¢
    0.08
    éĢļå¸¸åľ¨
    0.08
     main
    0.07
     íĬ¹íŀĪ
    0.07
    å®īåħ¨åĴĮ
    0.07
    çī¹åĪ¥
    0.07
    主è¦ģéĴĪ对
    0.07
    åIJĦèĩª
    0.07
    说æĺ¯
    0.07
    Activations Density 0.018%

    No Known Activations