© 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. 22892
    Prev
    Next
    INDEX
    Explanations

    square root of numbers and trigonometric functions

    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
    uzzi
    -0.08
    pired
    -0.08
    èĥ¤
    -0.08
    สุà¸Ķ
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    æľīåħ³è¦ģæ±Ĥ
    -0.07
    æģ¤
    -0.07
    é¼İé¼İ
    -0.07
    -END
    -0.07
     [@
    -0.07
    POSITIVE LOGITS
    ness
    0.08
    Ø©
    0.07
    illance
    0.07
    ëĤĺë§Ī
    0.07
    shire
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ëĤľ
    0.07
     nasty
    0.06
    ä»Ģä¹Īåij¢
    0.06
    teh
    0.06
    Activations Density 0.014%

    No Known Activations