© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37465
    Prev
    Next
    INDEX
    Explanations

    language translation and fluency

    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
    Negative Logits
    ãĥ³ãĥĹ
    -0.09
    insta
    -0.08
     brasil
    -0.07
    éĽģå¡Ķ
    -0.07
    schau
    -0.07
    åı¯ä¸į
    -0.07
    åı¯å°±
    -0.06
    lass
    -0.06
    ÙĨÙģ
    -0.06
    太å®Ī
    -0.06
    POSITIVE LOGITS
     bilingual
    0.10
    ilingual
    0.10
    åıĮè¯Ń
    0.10
     fluent
    0.10
     transl
    0.10
     linguistic
    0.09
     Lingu
    0.09
     untranslated
    0.08
     lingu
    0.08
    translator
    0.08
    Activations Density 0.036%

    No Known Activations