© 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. 37680
    Prev
    Next
    INDEX
    Explanations

    translation and translating

    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
    çĦ¶å¤§
    -0.08
    æĭŃ缮
    -0.07
    éĩij森
    -0.07
    éĥ½ä¸įéĶĻ
    -0.07
    ouser
    -0.07
    nev
    -0.06
    åĨ¥
    -0.06
    èİİ士
    -0.06
    è¿Ń
    -0.06
     insuf
    -0.06
    POSITIVE LOGITS
    edale
    0.07
    é¾IJ
    0.07
    éma
    0.07
    اث
    0.06
    rée
    0.06
    cate
    0.06
    eced
    0.06
    setQuery
    0.06
    _OPTS
    0.06
    rame
    0.06
    Activations Density 0.005%

    No Known Activations