© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33146
    Prev
    Next
    INDEX
    Explanations

    alarm threshold

    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
    è²¢
    -0.06
     yanı
    -0.06
    æľĢå¤ļ
    -0.06
    azzi
    -0.06
     simplest
    -0.06
    æĬĬä»ĸçļĦ
    -0.06
    å°±ç®ĹäºĨ
    -0.06
    åįģéĩĮ
    -0.06
    åĭĺ
    -0.06
    çª
    -0.06
    POSITIVE LOGITS
    å¾ĺå¾Ĭ
    0.09
     Alarm
    0.09
     alarm
    0.08
    大åħ³
    0.08
    Alarm
    0.08
    _threshold
    0.08
    éĺĪåĢ¼
    0.08
     Threshold
    0.08
    æİ¥è¿ij
    0.08
    Threshold
    0.08
    Activations Density 0.037%

    No Known Activations