© 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. 62411
    Prev
    Next
    INDEX
    Explanations

    stability and forces

    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
    обе
    -0.08
    篤
    -0.08
    arach
    -0.08
    稽
    -0.08
    æİĪæĿĥçļĦ
    -0.08
    æĪijçļĦç¥Ŀç¦ı
    -0.07
    ä¸Ģ鸣
    -0.07
    ambul
    -0.07
    æĸ¹å¼ı使çĶ¨
    -0.07
    otron
    -0.07
    POSITIVE LOGITS
    è¿Ļéĥ¨åĪĨ
    0.09
     contribution
    0.08
    æī£éĻ¤
    0.08
     minus
    0.08
    åĩıåİ»
    0.08
    øn
    0.08
    è´¡çĮ®
    0.08
     outweigh
    0.08
     incurred
    0.07
     contributions
    0.07
    Activations Density 0.007%

    No Known Activations