© 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. 10975
    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
    åĮ
    -0.08
    бов
    -0.07
    é¼ĵèĪŀ
    -0.07
    ãĤ±
    -0.06
     Huff
    -0.06
    fle
    -0.06
    ×ķ×Ĺ
    -0.06
     ape
    -0.06
     Frederick
    -0.06
    ivid
    -0.06
    POSITIVE LOGITS
    æĽ¦
    0.08
     פ×Ļ
    0.07
    æĻĸ
    0.07
    enom
    0.07
    天éķ¿
    0.07
    å£ĩ
    0.07
    åĿĽ
    0.07
     épouse
    0.07
    åħĥèµ·
    0.07
    æĥ³å¾Ĺ
    0.07
    Activations Density 0.000%

    No Known Activations