© 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. 13456
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and briefs

    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
    管çIJĨ软件
    -0.08
    landing
    -0.07
    缸åħ³æ³ķå¾ĭ责任
    -0.07
    -fw
    -0.07
    é¢Ĩ头ç¾Ĭ
    -0.07
    åıĸç¼Ķ
    -0.07
    éķ¿æľŁä½¿çĶ¨
    -0.07
    éĶĢåĶ®ä¸ļ绩
    -0.07
    çŁŃæľŁçļĦ
    -0.07
    oje
    -0.07
    POSITIVE LOGITS
    åħħåĪĨ
    0.10
     proceedings
    0.10
    åħħåĪĨçļĦ
    0.10
    è´¨è¯ģ
    0.09
     procedural
    0.08
    åħ¨ç¨ĭ
    0.08
     sten
    0.08
    åıĮæĸ¹
    0.08
    æ±¹
    0.08
    è¦ģåħħåĪĨ
    0.08
    Activations Density 0.217%

    No Known Activations