© 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. 23759
    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
    åIJ´æ±Ł
    -0.08
    å¦ĤçĥŁ
    -0.07
    (/[
    -0.07
    .asc
    -0.07
    å¦Ĥçİī
    -0.07
    ocks
    -0.07
    ä¸Ģè§ī
    -0.06
    åĮĸçī©
    -0.06
    .avi
    -0.06
    شد
    -0.06
    POSITIVE LOGITS
    åIJĪæł¼çļĦ
    0.08
    鹿
    0.07
    åIJĪæł¼
    0.06
    chure
    0.06
    éľĨ
    0.06
    chers
    0.06
    ä¸įå¾Ĺ以任ä½ķ
    0.06
    ucer
    0.06
    éĻIJå®ļ
    0.06
    çı¾
    0.06
    Activations Density 0.000%

    No Known Activations