© 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. 59044
    Prev
    Next
    INDEX
    Explanations

    "half", "two", "there", "it"

    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
    æį®ç»Łè®¡
    -0.07
    æį®
    -0.07
    äºĭå®ŀè¯ģæĺİ
    -0.07
    aturally
    -0.06
    HR
    -0.06
    During
    -0.06
    æĺİçĻ½
    -0.06
    æĢĢåŃķæľŁéĹ´
    -0.06
    表æĺİ
    -0.06
    ¾
    -0.06
    POSITIVE LOGITS
     Burl
    0.07
    punt
    0.07
    onga
    0.07
    |string
    0.07
    åĪĨä¹ĭ
    0.07
    auge
    0.07
    ä¸įåĪĨ
    0.06
    ãģ£ãģ¨
    0.06
    åıĹéªĹ
    0.06
    ane
    0.06
    Activations Density 0.069%

    No Known Activations