© 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. 48689
    Prev
    Next
    INDEX
    Explanations

    state of affairs or conditions

    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
    azon
    -0.08
    ilup
    -0.07
    æĮĩå°ĸ
    -0.07
    æī
    -0.07
    åįĥåı¤
    -0.07
     sonst
    -0.07
    å¿ĥæĦı
    -0.06
     лиÑĩной
    -0.06
    为çĪ±
    -0.06
    çļĦè¿Ļä¸Ģ
    -0.06
    POSITIVE LOGITS
    è¦ģä¸¥æł¼
    0.08
    ä¸ĢäºĽéĹ®é¢ĺ
    0.08
    æĿ¡ä»¶åĴĮ
    0.08
    ä¸Ģ鸣
    0.07
    ali
    0.07
    ä¸įè¿ĩåľ¨
    0.07
    çŃīçī¹çĤ¹
    0.07
    prot
    0.07
    _PARAMS
    0.07
    istream
    0.07
    Activations Density 2.887%

    No Known Activations