© 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. 31151
    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
    defaults
    -0.08
    ếng
    -0.08
     Ferrara
    -0.07
    æŀ«
    -0.07
    developers
    -0.07
    öpf
    -0.07
     excepción
    -0.07
    oldt
    -0.07
    åįģéĩĮ
    -0.07
    åı¯æĺ¯æĪij
    -0.07
    POSITIVE LOGITS
    è¿°
    0.07
    ç½¢
    0.07
    å®ĺåı¸
    0.07
    åĽ½åĨħå¤ĸ
    0.06
    ç½·
    0.06
    éĻĪè¿°
    0.06
    解æĶ¾
    0.06
    una
    0.06
    ä¸Ģ件
    0.06
    tm
    0.06
    Activations Density 0.000%

    No Known Activations