© 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. 4107
    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
    èĢĮè¿ĩ
    -0.08
    =re
    -0.08
    =context
    -0.07
    æk
    -0.06
    ç§ĭæľĪ
    -0.06
     jan
    -0.06
    idio
    -0.06
     Diper
    -0.06
    æĹ¥åħī
    -0.06
    serter
    -0.06
    POSITIVE LOGITS
    éĢı
    0.08
    å¾Ĺ主
    0.07
     конÑģо
    0.07
    åĴĮä¸įèī¯
    0.07
    ESC
    0.07
    主ä½ĵ
    0.07
    ijen
    0.07
    é§
    0.07
    .scss
    0.07
    anse
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.