© 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. 48563
    Prev
    Next
    INDEX
    Explanations

    heritage.com

    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
    ode
    -0.08
     gehabt
    -0.08
    åįĥçĻ¾
    -0.08
    å°Ĩè¾¾
    -0.08
    éĥ½ä»¥
    -0.08
    人æĦı
    -0.07
    è°ģ说
    -0.07
    åĵªäºĽéĹ®é¢ĺ
    -0.07
    surf
    -0.07
    ydi
    -0.07
    POSITIVE LOGITS
    è¿Ļ个æķ°åŃĹ
    0.09
    æĺ¯ä¸Ģ个å¾Ī
    0.08
     adalah
    0.08
    ãģ¨ãģĦãģĨãģ®ãģ¯
    0.08
     infatti
    0.07
     is
    0.07
    äºĶè¡Įå±ŀ
    0.07
     represents
    0.07
     bukanlah
    0.07
    (fig
    0.07
    Activations Density 0.013%

    No Known Activations