© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44564
    Prev
    Next
    INDEX
    Explanations

    `i` `since` `thread` `style`

    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
    Negative Logits
    æĹłäºº
    -0.08
    à¸Ħร
    -0.07
    çģ¿
    -0.07
    _Out
    -0.07
    æľªåıĸå¾Ĺ
    -0.07
    å®īå¹³
    -0.07
    enn
    -0.07
    æµ®çĶŁ
    -0.06
    ç»´
    -0.06
    commons
    -0.06
    POSITIVE LOGITS
    ä¸įä»ħèĥ½
    0.10
    æĽ´æĸ¹ä¾¿
    0.09
    æĺ¾å¾ĹæĽ´åĬł
    0.08
    acco
    0.08
    ä¸įä»ħåı¯ä»¥
    0.08
    ä¸įä»ħèĥ½å¤Ł
    0.08
    æĽ´å¿«
    0.08
    itier
    0.08
    顺便
    0.08
    æľīä»Ģä¹Ī好å¤Ħ
    0.08
    Activations Density 0.486%

    No Known Activations