© 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. 58053
    Prev
    Next
    INDEX
    Explanations

    saying something

    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
    witz
    -0.08
    大åĬŁ
    -0.07
    ä¸įæĦ§æĺ¯
    -0.07
    çģµæ´»
    -0.07
    津津
    -0.07
    æĻ®åĪ©
    -0.06
    éĽĦä¼Ł
    -0.06
    quel
    -0.06
    çĦķåıij
    -0.06
    è½
    -0.06
    POSITIVE LOGITS
    åĶ¯ç¾İçļĦ
    0.08
    è¿Ļæł·çļĦä¸Ģ个
    0.08
    é£İåIJ¹è¿ĩ
    0.08
    æĨĶæĤ´
    0.08
    æµħæµħ
    0.07
    éĻĮ
    0.07
    为äºĨæĽ´å¥½çļĦ
    0.07
    大éĥ¨ä»½
    0.07
    麽
    0.07
    èĤĨ
    0.07
    Activations Density 0.164%

    No Known Activations