© 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. 4804
    Prev
    Next
    INDEX
    Explanations

    passing serializable data

    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
     hierfür
    -0.08
     either
    -0.08
     outright
    -0.08
    è¦ģä¹Ī
    -0.07
     ovunque
    -0.07
    æĪĸæĺ¯
    -0.07
    elden
    -0.07
    isse
    -0.06
    让è¿ĻäºĽ
    -0.06
    isans
    -0.06
    POSITIVE LOGITS
     versus
    0.11
     vs
    0.08
    ä¸įå¾Ĺä¸į说
    0.08
    éĤ£çĤ¹
    0.07
    ãģ«ãģĬãģijãĤĭ
    0.07
     بدÙĦ
    0.07
     dynamics
    0.07
    æĺ¯åIJ¦ä¼ļ
    0.07
    ç»Īäºİåľ¨
    0.07
    AttributeValue
    0.07
    Activations Density 0.132%

    No Known Activations