© 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. 2039
    Prev
    Next
    INDEX
    Explanations

    warning lights and indicators

    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
    åĵĦ
    -0.08
    æĮŁ
    -0.07
    ZH
    -0.07
    缴æݥ影åĵį
    -0.07
     ÙĤص
    -0.07
    .addView
    -0.06
    оÑģо
    -0.06
    zeb
    -0.06
    åĩºä¸Ģ份
    -0.06
    å®ŀåľ¨æĺ¯
    -0.06
    POSITIVE LOGITS
    çĤ¹äº®
    0.11
    亮起
    0.09
     getStatus
    0.08
    示
    0.08
     flashing
    0.08
     indicating
    0.08
     Morse
    0.08
    indic
    0.08
    indle
    0.07
    igrations
    0.07
    Activations Density 0.028%

    No Known Activations