© 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. 60231
    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
     pos
    -0.06
    æĬĬä¸Ģ个
    -0.06
    ä¹ĭä¸į
    -0.06
    é«ĺå¯Ĩ
    -0.06
    _POS
    -0.06
     Zig
    -0.05
    åĽĬ
    -0.05
    ixin
    -0.05
    æĽ´ä¸įæĺ¯
    -0.05
    -pos
    -0.05
    POSITIVE LOGITS
    elang
    0.09
    еÑĩа
    0.08
    olon
    0.08
    undet
    0.08
     Lega
    0.08
    obe
    0.08
     afinal
    0.08
     Trudeau
    0.07
    anen
    0.07
    æĭĻ
    0.07
    Activations Density 0.000%

    No Known Activations