© 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. 33782
    Prev
    Next
    INDEX
    Explanations

    manufacturing methods and working principles

    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
    ousel
    -0.10
    ierer
    -0.09
    使çĶ¨åĴĮ
    -0.09
    æ£ĢæŁ¥åĴĮ
    -0.08
    æ³ķå¾ĭåĴĮ
    -0.08
    çļĦæĮĩ导ä¸ĭ
    -0.08
    å¤ĦçIJĨåĴĮ
    -0.08
    åħ®åħ®
    -0.08
    olan
    -0.08
    çļĦåĩºçİ°
    -0.08
    POSITIVE LOGITS
    æĸ¹å¼ı
    0.12
    æĸ¹å¼ı为
    0.12
    æĸ¹å¼ıåĴĮ
    0.09
    模å¼ı
    0.09
    è¿ĩç¨ĭ
    0.09
    å·²ä¹ħçļĦ
    0.09
    è¿ĩçļĦ
    0.08
    èĮĥåĽ´
    0.08
    æľºåĪ¶
    0.08
    /download
    0.08
    Activations Density 0.083%

    No Known Activations