© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23521
    Prev
    Next
    INDEX
    Explanations

    conditional logic 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
    Not in Any Lists

    No Comments

    Negative Logits
    æľīçĶŁ
    -0.08
     harmon
    -0.07
    éģ¨æ¸¸
    -0.07
    عÙĬ
    -0.07
     Boca
    -0.07
    浸润
    -0.07
    адÑĮ
    -0.07
    obook
    -0.06
     itemprop
    -0.06
    enburg
    -0.06
    POSITIVE LOGITS
    åĪĨæĶ¯
    0.11
     branches
    0.10
    (condition
    0.10
     logic
    0.10
     conditional
    0.10
     Logic
    0.10
    éĢ»è¾ij
    0.09
     switch
    0.09
     branching
    0.09
    è¯Ńåı¥
    0.09
    Activations Density 0.223%

    No Known Activations