© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13373
    Prev
    Next
    INDEX
    Explanations

    tree structures and hierarchy

    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
    èµ·æŃ¥
    -0.07
    çķ´
    -0.06
     Richardson
    -0.06
    毫
    -0.06
    ills
    -0.06
    大麦
    -0.06
    iliz
    -0.06
     Sper
    -0.06
    à¹Īาย
    -0.06
    è¿Ľä¸ĢæŃ¥æİ¨è¿Ľ
    -0.06
    POSITIVE LOGITS
     tree
    0.13
     Tree
    0.12
    æłijçļĦ
    0.12
    大æłij
    0.12
     trees
    0.12
    æłijå¹²
    0.12
    _tree
    0.12
    æłij
    0.12
    TreeNode
    0.12
    (TreeNode
    0.11
    Activations Density 0.021%

    No Known Activations