© 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. 55052
    Prev
    Next
    INDEX
    Explanations

    numbers and birth dates

    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
    åĴĮ
    -0.22
    ãĤĴ
    -0.14
    à¸Ĺีà¹Ī
    -0.13
    ë¡ľ
    -0.12
    ной
    -0.11
    ìĻĢ
    -0.10
    ãĤĴæķĻãģĪãģ¦
    -0.09
    ìĹIJ
    -0.09
    Ŀ
    -0.09
    ãĤĴçĻº
    -0.09
    POSITIVE LOGITS
    à¸ĩ
    0.08
    æĪĸåĪłéĻ¤
    0.08
    bé
    0.08
    缸åħ³èµĦ讯
    0.07
    <html
    0.07
     háºŃu
    0.07
    sieme
    0.07
    iach
    0.07
    uoj
    0.07
    >[]
    0.07
    Activations Density 0.350%

    No Known Activations