© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39727
    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
    linger
    -0.07
    èĬľ
    -0.07
    ViewState
    -0.07
    对ä¸Ĭè¿°
    -0.07
    à¸Łà¹īา
    -0.07
    anko
    -0.06
    èIJį
    -0.06
    åĪĺ家
    -0.06
    èĢĮ建
    -0.06
    ks
    -0.06
    POSITIVE LOGITS
    bower
    0.07
    noi
    0.07
    umbed
    0.07
    é¡¿
    0.07
    æĶ»åĿļæĪĺ
    0.07
    åľ¨ç»Ļ
    0.07
    è¶Ĭ
    0.06
    Guess
    0.06
    veis
    0.06
     Guess
    0.06
    Activations Density 0.000%

    No Known Activations