© 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. 44132
    Prev
    Next
    INDEX
    Explanations

    quoted phrases and phrases following punctuation

    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
    å¾Ĺåħ¶
    -0.08
    tring
    -0.07
    æľīçĶŁ
    -0.06
    ãģ¾ãģĹãģ¦
    -0.06
     Boh
    -0.06
    irates
    -0.06
     ÙħÙĤاÙħ
    -0.06
     comparable
    -0.06
    stal
    -0.06
    ugin
    -0.06
    POSITIVE LOGITS
    endre
    0.08
    WithData
    0.08
    oria
    0.07
    enu
    0.07
    ptos
    0.07
    CRET
    0.07
    ä¿Ŀéĩį
    0.07
     koll
    0.07
    âĨĵâĨĵ
    0.07
     ÄijÃłi
    0.07
    Activations Density 0.003%

    No Known Activations