© 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. 22438
    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
    åįĩ
    -0.07
    第
    -0.07
    å¾Ĺ罪
    -0.07
    ä¸įå¾Ĺè¶ħè¿ĩ
    -0.07
    iod
    -0.06
    ero
    -0.06
    .Dot
    -0.06
    åħ¨æĸĩ
    -0.06
    stick
    -0.06
    éĶ¥
    -0.06
    POSITIVE LOGITS
    éĥ¨ä»½
    0.08
    parate
    0.07
    åı¦å¤ĸä¸Ģç§į
    0.07
    alos
    0.07
    è¿Ľè¡Įä¸Ń
    0.07
    ä¸Ģ说
    0.07
    appa
    0.07
     postÄĻp
    0.07
    uman
    0.07
    riu
    0.07
    Activations Density 0.000%

    No Known Activations