© 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. 59051
    Prev
    Next
    INDEX
    Explanations

    masculine, Spanish, verbs, French, constructions

    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
    _DS
    -0.08
    æĵĤ
    -0.07
    ierra
    -0.07
    éĥ¨éŨåĴĮ
    -0.07
    watan
    -0.07
    çĶ±ä¼ģä¸ļ
    -0.07
    å°±æĺ¯æĪij们çļĦ
    -0.06
    _unset
    -0.06
    _unpack
    -0.06
    åı¯ä»¥çIJĨ解
    -0.06
    POSITIVE LOGITS
     verbs
    0.08
     Trad
    0.07
    .BASE
    0.07
    asha
    0.07
    æİĮæı¡
    0.07
    ç±»åĪ«
    0.07
     mastered
    0.07
    é»ij马
    0.07
    Įĵ
    0.07
    trad
    0.07
    Activations Density 0.003%

    No Known Activations