© 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. 44435
    Prev
    Next
    INDEX
    Explanations

    autocomplete search and prefix trie

    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
    _snap
    -0.07
    é¼ĵ
    -0.06
    å¿«çħ§
    -0.06
    stance
    -0.06
    ä¸Ĭ涨äºĨ
    -0.06
     Muda
    -0.06
    ä¿¡æģ¯æĿ¥æºIJ
    -0.06
     gathering
    -0.06
    æĢ»ä½ĵ
    -0.06
    æĺĵè´Ń
    -0.06
    POSITIVE LOGITS
    Prefix
    0.11
    prefix
    0.10
     Prefix
    0.10
     prefixes
    0.10
    uffix
    0.09
     endings
    0.09
     Kür
    0.09
    _prefix
    0.09
     prefix
    0.09
     shortest
    0.09
    Activations Density 0.029%

    No Known Activations