© 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. 58899
    Prev
    Next
    INDEX
    Explanations

    tree structures and branching

    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
    ago
    -0.07
     antaranya
    -0.07
     blasph
    -0.07
    ovar
    -0.06
    inha
    -0.06
     movers
    -0.06
     Bes
    -0.06
    _CAPTURE
    -0.06
    èĮĥåĽ´åĨħ
    -0.06
    èĮĥåĽ´çļĦ
    -0.06
    POSITIVE LOGITS
     tree
    0.14
    ä¸Ģ棵
    0.13
    æłij
    0.12
    æłijçļĦ
    0.12
     trees
    0.12
    æŀĿ
    0.12
     Tree
    0.11
    tree
    0.11
     pohon
    0.11
    TreeNode
    0.11
    Activations Density 0.031%

    No Known Activations