© 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. 38484
    Prev
    Next
    INDEX
    Explanations

    `cancelButtonTitle`, `word`, `words`, `text`

    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
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.09
    åĪ°çļĦ
    -0.09
    yeong
    -0.08
    orde
    -0.08
    çIJ¥
    -0.08
    _FATAL
    -0.08
    дом
    -0.07
    ÙģاÙĦ
    -0.07
    side
    -0.07
    uzzi
    -0.07
    POSITIVE LOGITS
    æł·çļĦ
    0.10
    ually
    0.09
    ÅĻejmÄĽ
    0.08
    人æ°ijæĶ¿åºľ
    0.08
    è¾Ī
    0.08
    å½¢çļĦ
    0.07
    å½ĵ头
    0.07
    ephir
    0.07
    éĹ´çļĦ
    0.07
    alog
    0.07
    Activations Density 0.002%

    No Known Activations