© 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. 42722
    Prev
    Next
    INDEX
    Explanations

    expression syntax

    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
    山寨
    -0.08
    yez
    -0.08
    åģĩåĨĴ
    -0.07
     procedura
    -0.07
    statuses
    -0.07
    ecte
    -0.07
    æĿİ建
    -0.07
    BootTest
    -0.07
    Ù°
    -0.07
     stagger
    -0.07
    POSITIVE LOGITS
     syntax
    0.11
    表达
    0.11
     expression
    0.10
     expressions
    0.10
    expression
    0.09
    -expression
    0.09
    -syntax
    0.09
    _syntax
    0.09
    expr
    0.09
    è¯Ńæ³ķ
    0.09
    Activations Density 0.526%

    No Known Activations