© 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. 21267
    Prev
    Next
    INDEX
    Explanations

    list separators and subsequent instructions

    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
     otherwise
    -0.08
    otherwise
    -0.08
    åIJ¦åĪĻä¼ļ
    -0.08
    å¿«æĬ¥
    -0.07
    ync
    -0.07
    ãģĤãģ£ãģ¦
    -0.07
    家åĸ»
    -0.07
    張貼
    -0.07
    abol
    -0.07
    anders
    -0.07
    POSITIVE LOGITS
    æĮīçħ§è§Ħå®ļ
    0.09
    æĮīçħ§
    0.07
     apply
    0.07
    æ¯Ķè¾ĥå°ı
    0.07
    åĪ¤ä»¤
    0.07
    çĶ¨
    0.07
    éĻĦä¸Ĭ
    0.07
    该楼å±Ĥçĸijä¼¼è¿Ŀè§Ħå·²è¢«ç³»ç»ŁæĬĺåıł
    0.07
    大èĥĨ
    0.07
    å¥ĹçĶ¨
    0.06
    Activations Density 0.010%

    No Known Activations