© 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. 10322
    Prev
    Next
    INDEX
    Explanations

    translation, translator, or transliteration

    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
     diagnos
    -0.06
    认è¯Ĩ
    -0.06
     mixin
    -0.06
    ascin
    -0.06
    æ±°
    -0.06
     Ord
    -0.06
    iah
    -0.06
    æľīçĶ¨
    -0.06
    çļĦ主è§Ĵ
    -0.06
    ëģĪ
    -0.06
    POSITIVE LOGITS
     translators
    0.12
    å¿łå®ŀ
    0.12
     translations
    0.11
     translation
    0.11
     translator
    0.11
     пеÑĢевод
    0.11
     transl
    0.11
    è¯ijæĸĩ
    0.10
    åİŁæĸĩ
    0.10
    åİŁä½ľ
    0.10
    Activations Density 0.037%

    No Known Activations