© 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. 61069
    Prev
    Next
    INDEX
    Explanations

    difficult to understand or do

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    æłijä¸Ģ
    -0.07
    äºĨä¸ĢåĪĩ
    -0.07
    ificates
    -0.07
    åĺģ
    -0.07
     непÑĢеменно
    -0.07
    åı¯ä»¥åIJĹ
    -0.07
     sortes
    -0.07
    åīįåħĪ
    -0.07
    ä¸ĩä¸ĩ
    -0.07
    POSITIVE LOGITS
    ä¹Łå®¹æĺĵ
    0.12
    ä¹Łå¾Īéļ¾
    0.12
     easily
    0.09
     nowadays
    0.09
    éļ¾ä»¥
    0.09
    å¾Īéļ¾
    0.09
    å¾ĪéĽ£
    0.09
    å°¤åħ¶æĺ¯åľ¨
    0.09
    ä¸Ģä¸įå°ıå¿ĥ
    0.09
    ä¸į容æĺĵ
    0.09
    Activations Density 0.274%

    No Known Activations