© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62999
    Prev
    Next
    INDEX
    Explanations

    starts with "Well" or "Yeah"

    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
    æĹ¥åĩĮæĻ¨
    -0.08
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    åł¡
    -0.07
    天马
    -0.07
    åįģ大
    -0.07
    iggio
    -0.07
     ded
    -0.07
    emaan
    -0.07
    è¿Ļ群
    -0.07
    _Impl
    -0.07
    POSITIVE LOGITS
    èī¯
    0.07
    zm
    0.07
    usher
    0.06
    ä¹Łä¸įçĶ¨
    0.06
    åį¡
    0.06
    æ
    0.06
    R
    0.06
    Ùħز
    0.06
    t
    0.06
    çī©çIJĨ
    0.06
    Activations Density 0.025%

    No Known Activations