© 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. 63962
    Prev
    Next
    INDEX
    Explanations

    syntax and code constructs

    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
    ×Ļ׾×ķ
    -0.08
    ãģĭãģ®
    -0.07
    ãģĭãĤı
    -0.07
    _depend
    -0.07
    statt
    -0.07
    éĢĢäºĨ
    -0.07
    obl
    -0.07
    oucher
    -0.07
    oppen
    -0.07
    IFT
    -0.07
    POSITIVE LOGITS
    ä¹į
    0.08
    æĻĵå¾Ĺ
    0.07
    å±¥åİĨ
    0.06
     conting
    0.06
    eler
    0.06
     vite
    0.06
    å
    0.06
    æĽ¾åĽł
    0.06
    身份è¯ģ
    0.06
    èıł
    0.06
    Activations Density 0.002%

    No Known Activations