© 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. 57027
    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
    ç»Ŀåľ°
    -0.08
    beck
    -0.08
    个æĪĸå¤ļ个
    -0.08
    ancen
    -0.08
    ì²Ļ
    -0.08
    å®īåİ¿
    -0.07
    acer
    -0.07
    好çİ©
    -0.07
    è¿Ļåıªæĺ¯
    -0.07
    alous
    -0.07
    POSITIVE LOGITS
    ä¹ĭä¸ĢçļĦ
    0.08
    ä¾Ŀæ³ķ
    0.07
    ç»ı
    0.07
    ç®
    0.06
    éĻIJåĪ¶äºĨ
    0.06
    UDGE
    0.06
    ood
    0.06
     processed
    0.06
    ãģĿãĤį
    0.06
    é¼İ缼
    0.06
    Activations Density 0.000%

    No Known Activations