© 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. 14947
    Prev
    Next
    INDEX
    Explanations

    programming languages and topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    对äºİè¿ĻäºĽ
    -0.10
    对äºİè¿Ļ个
    -0.10
    对äºİ
    -0.09
     für
    -0.08
     untuk
    -0.08
     voor
    -0.08
    对äºİéĤ£äºĽ
    -0.08
    对äºİä¸Ģ个
    -0.08
     dla
    -0.08
     длÑı
    -0.07
    POSITIVE LOGITS
     purposes
    0.22
     sake
    0.22
     Zwecke
    0.18
    人æĿ¥è¯´
    0.18
    æĿ¥è¯´æĺ¯
    0.16
    èĢĮè¨Ģ
    0.15
    æĿ¥è¯´
    0.15
    çļĦ人æĿ¥è¯´
    0.14
     ÙĪÙĦÙĦ
    0.14
    æĪijæĿ¥è¯´
    0.13
    Activations Density 0.878%

    No Known Activations