© 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. 45396
    Prev
    Next
    INDEX
    Explanations

    trigonometric substitution

    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
    æį®æĤī
    -0.10
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.10
    è¿ĩç¥ŀ
    -0.09
    个人认为
    -0.09
    å¤įåĪ»
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    bero
    -0.09
    udos
    -0.09
    åIJ¬éĹ»
    -0.09
    尿裤
    -0.08
    POSITIVE LOGITS
    å¦ĤåĽ¾
    0.07
    ↵↵
    0.07
     tremendous
    0.07
     Chapter
    0.07
     shorthand
    0.07
    —we
    0.07
     CHAPTER
    0.07
     Fig
    0.06
     Figure
    0.06
     enormously
    0.06
    Activations Density 0.056%

    No Known Activations