© 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. 60069
    Prev
    Next
    INDEX
    Explanations

    groups, subsets, clusters

    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
    æĹłå¤Ħä¸įåľ¨
    -0.08
    ainment
    -0.08
    åıĮ线
    -0.07
    _super
    -0.07
    åį¸
    -0.07
    ä¸ĩ件
    -0.07
     vielf
    -0.07
    jal
    -0.07
    ä¸ĩåIJį
    -0.07
     Extra
    -0.07
    POSITIVE LOGITS
     grouping
    0.12
    æ¯ıç»Ħ
    0.11
     subsets
    0.11
     grouped
    0.10
     groups
    0.10
    ãģ¾ãģ¨
    0.10
    æŁIJä¸Ģ
    0.09
    åľ¨æŁIJ
    0.09
    æŁIJ个
    0.09
    éĽĨä¸Ń
    0.09
    Activations Density 0.283%

    No Known Activations