© 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. 30389
    Prev
    Next
    INDEX
    Explanations

    friction stir welding processes

    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
    åIJijæ³ķéĻ¢
    -0.07
    踩
    -0.06
    梳
    -0.06
     imprison
    -0.06
     beat
    -0.06
    æ¡
    -0.06
    榨
    -0.06
     tur
    -0.06
    秣éĩij
    -0.06
    å¸Ī大
    -0.06
    POSITIVE LOGITS
     weld
    0.14
    çĦĬ
    0.14
     welding
    0.13
    çĦĬç¼Ŀ
    0.13
    çĦĬæİ¥
    0.12
     Weld
    0.12
    çĦĬå·¥
    0.11
     ÑģваÑĢ
    0.11
    çĦĬæľº
    0.11
     welded
    0.10
    Activations Density 0.046%

    No Known Activations