© 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. 42165
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åīįè¿°
    -0.07
    еÑĩи
    -0.07
    移èĩ³
    -0.07
    ä¸Ĭè¿°äºĭå®ŀ
    -0.07
    Ãłng
    -0.06
    使ä¹ĭ
    -0.06
    æŶèĢĮ
    -0.06
     dial
    -0.06
    sans
    -0.06
    èĩªçŁ¥
    -0.06
    POSITIVE LOGITS
    æľīè¿Ļä¹Ī
    0.08
    åīįèĮħ
    0.08
    akh
    0.07
    ELLI
    0.07
    [Math
    0.07
    æĺ¯è¦ģ
    0.07
    éĹ®é¢ĺæĺ¯
    0.07
    "><!--
    0.07
    ç¶
    0.07
    IMIT
    0.07
    Activations Density 0.000%

    No Known Activations