© 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. 45233
    Prev
    Next
    INDEX
    Explanations

    published, awarded, frequent speaker, featured, appeared

    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
     ideally
    -0.08
    æĪij们åħĪ
    -0.07
     th
    -0.07
    [^
    -0.07
     thugs
    -0.07
    æĪij们è¿ĻäºĽ
    -0.07
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    -0.07
    åĪļ好
    -0.07
    æŃ£å¥½
    -0.07
    æģ°å¥½
    -0.07
    POSITIVE LOGITS
     extensively
    0.09
    çŃīå¤ļ项
    0.09
     numerous
    0.08
     inoltre
    0.08
    å¤ļ次
    0.08
     számos
    0.08
    åIJĦç±»
    0.07
    çļĦåIJĦç±»
    0.07
    éŃĤ
    0.07
     Ø£ÙĬضا
    0.07
    Activations Density 0.805%

    No Known Activations