© 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. 55065
    Prev
    Next
    INDEX
    Explanations

    esteem, semiconductor, description

    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
    ãģŁãĤģãģ®
    -0.07
    gatsby
    -0.06
     against
    -0.06
    моÑĤÑĢ
    -0.06
    éĥ½åľ¨
    -0.06
    éĿ¢å¯¹
    -0.06
    ä¼ģä¸ļ对
    -0.06
    ä¸įçĽ¸ä¿¡
    -0.06
    çľĭä¸Ĭ
    -0.06
    为ä»Ģä¹Ī
    -0.06
    POSITIVE LOGITS
    æŃ¤èµ·
    0.14
    çļĦä¸ĢåĪĩéĥ½
    0.11
    åĨħ容æľī
    0.10
    æĿ¥è¯´æĺ¯
    0.10
    羣å®ŀæĢ§è´Łè´£
    0.09
    æĦıä¹īéĩį大
    0.09
    ))^
    0.09
    å¾Ĺèµ·
    0.09
    çĪ±ä¸į
    0.09
    ç«ĭåľºæĹłåħ³
    0.09
    Activations Density 0.004%

    No Known Activations