© 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. 22796
    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
    åľ¨ç¾İ
    -0.07
    els
    -0.07
    åIJŀåIJIJ
    -0.06
    è´£ç¼ĸ
    -0.06
    侦æİ¢
    -0.06
     Fra
    -0.06
    ÑĪаÑĤ
    -0.06
    éĺ
    -0.06
    å°Ķæĸ¯
    -0.06
    èĮĦ
    -0.06
    POSITIVE LOGITS
    该款
    0.10
    æĥħå½¢
    0.09
    åºĶå½ĵåľ¨
    0.09
    æĥħå½¢çļĦ
    0.09
    åºĶå½ĵæĮīçħ§
    0.09
    å¤ĦçIJĨçļĦ
    0.08
    åºĶå½ĵä¾Ŀçħ§
    0.08
    иÑģÑĮ
    0.08
    æ³ķå¾ĭè§Ħå®ļ
    0.08
    æĹłæĿĥ
    0.08
    Activations Density 0.000%

    No Known Activations