© 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. 12788
    Prev
    Next
    INDEX
    Explanations

    seems that

    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
    ãģ®ãģĵãģ¨
    -0.08
    ä¸įä»ħä»ħæĺ¯
    -0.07
    é¦
    -0.07
    à¸Ĺัà¹īà¸ĩสิà¹īà¸Ļ
    -0.06
    彤
    -0.06
    åįĥåı¤
    -0.06
    ä¸įæĺ¯è¯´
    -0.06
    ä¼ł
    -0.06
    aber
    -0.06
    湧
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.16
    ãģĵãģ¡ãĤīãĤĤ
    0.13
    ä¹Łæĺ¯éĿŀ常
    0.13
     ÑĤоже
    0.11
    ä¹Łæĺ¯å¾Ī
    0.11
    ãģĵãĤĮãĤĤ
    0.11
    çŃīåħ¶ä»ĸ
    0.11
    主è¦ģçĶ¨äºİ
    0.11
     another
    0.11
    another
    0.11
    Activations Density 0.066%

    No Known Activations