© 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. 28931
    Prev
    Next
    INDEX
    Explanations

    indicating or signaling status

    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
    对æīĭçļĦ
    -0.08
    éĹ»è¨Ģ
    -0.07
    ÑĢенд
    -0.06
    å¸Ĥæ°ijçļĦ
    -0.06
    olum
    -0.06
    åĽłæĤ¨çļĦ
    -0.06
    è°Ī
    -0.06
    对ä»ĺ
    -0.06
    rell
    -0.06
    表çݰ为
    -0.06
    POSITIVE LOGITS
     intent
    0.10
     intention
    0.09
    表æĺİ
    0.09
     intended
    0.08
    Intent
    0.08
    intent
    0.08
     impending
    0.08
    大åĬŁ
    0.08
     Intent
    0.08
    æĦıåĽ¾
    0.08
    Activations Density 0.195%

    No Known Activations