© 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. 26283
    Prev
    Next
    INDEX
    Explanations

    recent events and status updates

    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
    åľ¨å½ĵæŶ
    -0.10
    åĬłä»¥
    -0.09
     decades
    -0.09
     centuries
    -0.08
    éĢIJå¹´
    -0.08
    æŶ任
    -0.08
     ultimately
    -0.07
    è¾ħ以
    -0.07
    èµ°ä¸ĭåİ»
    -0.07
     decenni
    -0.07
    POSITIVE LOGITS
    æľīæĸ°çļĦ
    0.11
     lately
    0.10
    recent
    0.10
    æľīäºĨæĸ°çļĦ
    0.09
     вÑĩеÑĢа
    0.09
     recent
    0.09
    æĺ¨å¤ľ
    0.09
    æĸ°çļĦ
    0.09
     recently
    0.09
    èIJ½å®ŀæĥħåĨµ
    0.09
    Activations Density 1.424%

    No Known Activations