© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 38651
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    spur
    -0.07
    é¹ı
    -0.07
    ocat
    -0.06
    entic
    -0.06
    нин
    -0.06
     Pesc
    -0.06
    à¤Ĥत
    -0.06
    鹤
    -0.06
    çļĦä»»ä½ķ
    -0.06
    åħ°å¾·
    -0.06
    POSITIVE LOGITS
    æĪĸæľī
    0.07
    linger
    0.07
    ger
    0.07
    æĪĸèĢħæľī
    0.07
    æĺĮåİ¿
    0.07
    lingen
    0.07
    ikka
    0.07
    à¸ļาย
    0.07
    æĹłèĻij
    0.07
     chÄĥng
    0.07
    Activations Density 0.000%

    No Known Activations