© 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. 58580
    Prev
    Next
    INDEX
    Explanations

    dose-limiting

    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
    顾åıĬ
    -0.08
    spre
    -0.07
    两å¥Ĺ
    -0.07
    åıĹçĽĬäºİ
    -0.07
    izzo
    -0.07
    StateException
    -0.07
    igli
    -0.07
    çļĦå®ŀéªĮ
    -0.07
    Lot
    -0.07
     dÃłnh
    -0.07
    POSITIVE LOGITS
    çļĦ主è¦ģåĽłç´ł
    0.09
    çļĦéĩįè¦ģåĽłç´ł
    0.08
     uniquely
    0.07
     otherwise
    0.07
    roker
    0.07
    çļĦéĩįè¦ģä¾Ŀæį®
    0.07
    çļĦ主è¦ģåĨħ容
    0.07
    ivating
    0.07
    å°±åľ¨äºİ
    0.07
    ä¹ŁæŃ£æĺ¯
    0.07
    Activations Density 0.220%

    No Known Activations